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

    Neuronpedia

    INDEX
    Explanations

    references to video games and specific game titles

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Lobby
    -0.73
     glim
    -0.64
    worth
    -0.59
     bleach
    -0.59
     ferment
    -0.59
     clerks
    -0.59
    ŃĶ
    -0.59
     Financial
    -0.57
    amount
    -0.56
    yards
    -0.56
    POSITIVE LOGITS
    unction
    0.97
    oj
    0.93
    agy
    0.88
    itsu
    0.87
    angles
    0.86
    acket
    0.86
    ournal
    0.85
    ombie
    0.85
    atche
    0.85
    awaru
    0.84
    Act Density 7.605%

    No Known Activations