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

    Neuronpedia

    INDEX
    Explanations

    references to scientific concepts and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SS
    -0.64
    cS
    -0.56
    SB
    -0.55
    pS
    -0.54
    SL
    -0.52
    /*++
    -0.51
    AS
    -0.51
    sb
    -0.51
    SA
    -0.49
    SSSS
    -0.49
    POSITIVE LOGITS
     sérieux
    0.61
     himſelf
    0.59
     scolaires
    0.56
     ſhall
    0.55
     spéciales
    0.55
     scientifique
    0.54
    +:+
    0.54
    writeFieldEnd
    0.54
     Majefty
    0.53
     success
    0.53
    Act Density 0.557%

    No Known Activations