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

    Neuronpedia

    INDEX
    Explanations

    information relating to announcements, press releases, and business developments

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     laughter
    -0.76
     whine
    -0.70
     doubles
    -0.69
     Trog
    -0.68
     doct
    -0.67
     extrad
    -0.65
     charm
    -0.64
     minus
    -0.62
     hust
    -0.61
     manoeuv
    -0.61
    POSITIVE LOGITS
    ³³³
    1.19
    ³³³³³³³³³³³³³³³³
    1.17
    ³³³³
    1.10
    ³³³³³³³³
    1.05
    ³³
    0.92
    Prior
    0.92
    ccording
    0.91
    Contents
    0.89
    Currently
    0.85
    Its
    0.84
    Act Density 0.646%

    No Known Activations