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

    Neuronpedia

    INDEX
    Explanations

    references to specific characters or names in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -1.22
     Anſ
    -1.16
     Monfieur
    -1.15
     ―――――
    -1.08
     Eſ
    -1.07
     Beſ
    -1.04
     raiſ
    -1.03
     itſelf
    -1.01
     Reſ
    -0.98
    BibitemShut
    -0.98
    POSITIVE LOGITS
     Ke
    0.76
    flo
    0.69
     flo
    0.67
    {$
    0.64
    Ke
    0.60
     प
    0.60
     ke
    0.58
    Flo
    0.58
     Flo
    0.57
    Handle
    0.57
    Act Density 0.228%

    No Known Activations