© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 865
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "little" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izoph
    -0.81
    thal
    -0.79
    poon
    -0.79
    kus
    -0.73
    strate
    -0.72
    lyak
    -0.67
    pes
    -0.65
    ply
    -0.65
    aston
    -0.65
     Converted
    -0.64
    POSITIVE LOGITS
     separates
    0.72
     touches
    0.71
     else
    0.69
     survives
    0.67
     mattered
    0.65
     names
    0.65
     identifies
    0.63
     except
    0.63
     besides
    0.63
     appreciated
    0.62
    Activations Density 0.023%

    No Known Activations