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

    Neuronpedia

    INDEX
    Explanations

    comments in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.00
     ſeveral
    -0.98
     myſelf
    -0.97
     Monfieur
    -0.88
     Chriftian
    -0.85
     ſtate
    -0.84
     juſt
    -0.82
     raiſ
    -0.81
    ſelf
    -0.80
     themſelves
    -0.80
    POSITIVE LOGITS
     //
    1.14
    //
    0.90
    ///
    0.64
     Ngb
    0.63
    setVerticalGroup
    0.63
    //
    0.61
    //////
    0.59
     (
    0.59
     "
    0.57
     π
    0.56
    Act Density 0.123%

    No Known Activations