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

    Neuronpedia

    INDEX
    Explanations

    code-related conditions or checks in programming structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -2.97
     myſelf
    -2.91
     Efq
    -2.86
     Monfieur
    -2.76
     ―――――
    -2.63
     ་་
    -2.63
     Jefus
    -2.62
     Majefty
    -2.62
     Anſ
    -2.58
     Theſe
    -2.52
    POSITIVE LOGITS
     
    1.73
    ,
    1.54
     (
    1.51
     in
    1.36
     a
    1.31
    .
    1.29
     to
    1.29
    ↵↵
    1.23
    <eos>
    1.22
     [
    1.18
    Act Density 2.138%

    No Known Activations