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

    Neuronpedia

    INDEX
    Explanations

    chemical elements and symbols

    oai_token-act-pair · gpt-3.5-turbo

    combinations of letters and potential abbreviations or codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ways
    -0.66
     seiz
    -0.63
     attrition
    -0.63
     centrif
    -0.62
     surg
    -0.57
    ¥µ
    -0.56
     plur
    -0.56
    jriwal
    -0.56
    azeera
    -0.55
     coli
    -0.55
    POSITIVE LOGITS
    ongyang
    0.86
    asus
    0.84
    γ
    0.81
    ciation
    0.79
    sylvania
    0.77
    Äĩ
    0.76
    sburgh
    0.75
    ucket
    0.75
    Cola
    0.74
     Nieto
    0.73
    Act Density 0.533%

    No Known Activations