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

    Neuronpedia

    INDEX
    Explanations

    ancient and historical names or terms with unusual characters or spellings

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    heed
    -0.88
    ¥µ
    -0.86
     rall
    -0.84
     Amos
    -0.80
    pled
    -0.79
     modem
    -0.75
    ctica
    -0.73
     Bots
    -0.73
    coni
    -0.72
    cible
    -0.72
    POSITIVE LOGITS
    keye
    1.23
    icago
    1.15
    rome
    1.07
    annel
    1.06
    ynski
    1.04
    otomy
    1.03
    sen
    0.99
    onne
    0.99
    ards
    0.98
    oly
    0.98
    Act Density 6.532%

    No Known Activations