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

    Neuronpedia

    INDEX
    Explanations

    terms related to strategies and decision-making

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    NetMessage
    -0.88
    steamapps
    -0.73
    tyard
    -0.71
     KING
    -0.69
     PHOTO
    -0.69
     Alive
    -0.67
    vity
    -0.66
    spread
    -0.66
     Citation
    -0.65
    nikov
    -0.65
    POSITIVE LOGITS
     awaits
    0.77
     thou
    0.74
     transpired
    0.72
     happens
    0.71
     survives
    0.71
    soever
    0.71
     deems
    0.70
    amac
    0.70
    yip
    0.69
     they
    0.69
    Act Density 16.251%

    No Known Activations