© 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. 919
    Prev
    Next
    INDEX
    Explanations

    instances of the word "perhaps."

    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
    itars
    -0.86
    gd
    -0.76
    ■
    -0.74
    ••
    -0.73
    ILS
    -0.72
    duction
    -0.72
    XT
    -0.72
    Posts
    -0.71
     Topics
    -0.69
    ¶
    -0.69
    POSITIVE LOGITS
     predictably
    0.95
     undes
    0.79
     unsurprisingly
    0.76
     nowhere
    0.75
     overlooked
    0.75
     deadliest
    0.74
     easiest
    0.73
     toughest
    0.73
     understandable
    0.72
     quickest
    0.72
    Activations Density 0.039%

    No Known Activations