Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    questions and expressions of expectation or uncertainty

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Portail
    -0.52
     Seligman
    -0.52
    неров
    -0.52
    ifun
    -0.52
     beho
    -0.51
    ethene
    -0.51
     davon
    -0.50
     '.')
    -0.50
    confirm
    -0.49
    CppCodeGen
    -0.49
    POSITIVE LOGITS
    expandindo
    0.69
    ImageContext
    0.66
    Zacks
    0.63
    Diweddarwch
    0.59
    LikeLiked
    0.56
    󠁢
    0.56
    httphttps
    0.55
    aarrggbb
    0.54
     <<<<<<<<<<<<<<
    0.52
     lenker
    0.52
    Act Density 0.261%

    No Known Activations