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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods and quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    athan
    -0.17
    ware
    -0.15
    throp
    -0.14
    avo
    -0.14
    -di
    -0.14
     Vak
    -0.14
    quoi
    -0.13
    Sortable
    -0.13
    ensor
    -0.13
    orks
    -0.13
    POSITIVE LOGITS
    luet
    0.18
     addCriterion
    0.18
    TI
    0.16
    ió
    0.15
    éħ
    0.15
    izza
    0.15
    foy
    0.15
    OLON
    0.14
     Truy
    0.14
     ì·¨
    0.14
    Act Density 0.003%

    No Known Activations