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

    Neuronpedia

    INDEX
    Explanations

    financial or numerical references

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'Q'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Magicka
    -0.73
    éĹĺ
    -0.71
     birth
    -0.69
    coni
    -0.68
    ãĤ¢
    -0.67
     fullest
    -0.66
     waking
    -0.63
     heart
    -0.61
     ages
    -0.61
     kicking
    -0.61
    POSITIVE LOGITS
    Q
    1.00
    addafi
    0.97
    UE
    0.95
    WER
    0.93
    TT
    0.92
    irements
    0.88
    DN
    0.85
    atari
    0.84
    MJ
    0.83
    atar
    0.81
    Act Density 0.009%

    No Known Activations