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

    Neuronpedia

    INDEX
    Explanations

    pricing details related to subscription plans

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ibaba
    -1.13
     showc
    -1.08
    uphem
    -1.00
    acerb
    -1.00
    glomer
    -0.99
    inational
    -0.95
     subsequ
    -0.94
    emort
    -0.93
    idth
    -0.89
     misunder
    -0.89
    POSITIVE LOGITS
    Pixel
    1.02
    Bernie
    0.95
    YC
    0.92
    AMY
    0.89
    ON
    0.88
    venture
    0.88
    Spons
    0.84
    AY
    0.83
    arson
    0.83
    email
    0.82
    Act Density 0.191%

    No Known Activations