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

    Neuronpedia

    INDEX
    Explanations

    causal relationships and explanations within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ondon
    -0.16
    hq
    -0.15
    ä¸Ńåįİ
    -0.15
    åijĺ
    -0.14
    imet
    -0.14
    лина
    -0.14
    anim
    -0.13
    аÑĤив
    -0.13
    insi
    -0.13
    лова
    -0.13
    POSITIVE LOGITS
     its
    0.17
     оно
    0.15
    å®ĥ
    0.14
    pios
    0.14
    ColumnInfo
    0.14
     Vern
    0.14
    íĭ
    0.14
    wald
    0.13
    ¦
    0.13
    VarChar
    0.13
    Act Density 0.122%

    No Known Activations