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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.97
     дописавши
    -1.86
     myſelf
    -1.84
     Monfieur
    -1.69
     Efq
    -1.67
     doubtnut
    -1.62
     Houſe
    -1.61
     Majefty
    -1.59
     Anſ
    -1.59
     ་་
    -1.58
    POSITIVE LOGITS
    ,
    1.26
    .
    1.21
     (
    0.99
    ↵↵
    0.96
    ↵
    0.94
     
    0.88
    -
    0.84
     a
    0.84
     and
    0.81
     .
    0.80
    Act Density 1.134%

    No Known Activations