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

    Neuronpedia

    INDEX
    Explanations

    dates in the format month, day, year

    oai_token-act-pair · gpt-3.5-turbo

    punctuation or symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Si
    -0.90
     Takeru
    -0.90
     Sag
    -0.89
     Sai
    -0.88
    ãĥĨãĤ£
    -0.87
    SI
    -0.86
    Cas
    -0.85
     Sage
    -0.85
    sg
    -0.84
    Si
    -0.84
    POSITIVE LOGITS
    uph
    0.96
    2017
    0.93
    bern
    0.87
    uron
    0.87
     2017
    0.85
    ber
    0.83
    aud
    0.80
    zan
    0.79
    oust
    0.77
    unk
    0.75
    Act Density 0.442%

    No Known Activations