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

    Neuronpedia

    INDEX
    Explanations

    parenthetical expressions or notes in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apter
    -0.19
    oft
    -0.18
    uft
    -0.17
    ault
    -0.17
    eck
    -0.15
    олож
    -0.14
    hev
    -0.14
    è»Ł
    -0.14
    oure
    -0.14
    .wr
    -0.13
    POSITIVE LOGITS
     one
    0.22
    ä¸Ģ个
    0.19
     eines
    0.16
    }elseif
    0.16
     íķĺëĤĺ
    0.15
     má»Ļt
    0.14
    ajor
    0.14
    2
    0.14
    ishi
    0.14
     legitim
    0.14
    Act Density 0.053%

    No Known Activations