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

    Neuronpedia

    INDEX
    Explanations

    specific formatting or markup elements, particularly related to URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -1.12
     myſelf
    -1.03
    WriteBarrier
    -0.99
     purpoſe
    -0.97
    SharedDtor
    -0.97
     Majefty
    -0.96
    ſelf
    -0.93
     itſelf
    -0.92
     мәкал
    -0.91
     ſeveral
    -0.91
    POSITIVE LOGITS
     
    0.62
     (
    0.58
     or
    0.52
    /
    0.50
     even
    0.48
     "
    0.47
    (
    0.47
    ↵↵
    0.47
     past
    0.46
    もなく
    0.46
    Act Density 0.188%

    No Known Activations