© 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. 766
    Prev
    Next
    INDEX
    Explanations

    references to combinations of elements or factors

    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
    milo
    -0.69
    inki
    -0.68
    azel
    -0.68
    Magikarp
    -0.66
    闘
    -0.66
    atro
    -0.65
    htar
    -0.64
    phia
    -0.64
     skelet
    -0.63
    align
    -0.63
    POSITIVE LOGITS
     thereof
    0.80
     of
    0.71
     OF
    0.69
     Of
    0.67
     Between
    0.61
     Whereas
    0.59
    Of
    0.57
     Enter
    0.57
    "],"
    0.56
    laughter
    0.53
    Activations Density 0.083%

    No Known Activations