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

    Neuronpedia

    INDEX
    Explanations

    mathematical optimization expressions, specifically related to minimization problems

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.75
     ſtand
    -0.70
     myſelf
    -0.65
     Jefus
    -0.64
     pleaſure
    -0.64
     ſtate
    -0.62
     itſelf
    -0.62
     BoxFit
    -0.61
     Monfieur
    -0.61
     raiſ
    -0.59
    POSITIVE LOGITS
    classnames
    0.64
    IsMutable
    0.63
     colspan
    0.61
    quoi
    0.58
    жку
    0.58
    '])){
    0.55
    راع
    0.54
    }');
    0.54
     poche
    0.52
    createQuery
    0.52
    Act Density 0.009%

    No Known Activations