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

    Neuronpedia

    INDEX
    Explanations

    words related to music and performance

    oai_token-act-pair · gpt-3.5-turbo

    contextual references to confidence and self-assurance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "...
    -0.67
     "-
    -0.64
    Unix
    -0.64
    Transform
    -0.63
     filib
    -0.60
     Outs
    -0.59
    Availability
    -0.57
    Brend
    -0.56
     incorpor
    -0.56
    Stage
    -0.55
    POSITIVE LOGITS
    ggle
    0.79
    chester
    0.74
    otine
    0.73
    ':
    0.73
     ',
    0.72
    ngth
    0.72
    azard
    0.72
    apest
    0.70
    orie
    0.69
    wcsstore
    0.69
    Act Density 0.548%

    No Known Activations