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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing something as complete or thorough

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating completeness or totality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.90
     Disciple
    -0.83
    achu
    -0.73
     Pike
    -0.71
    */(
    -0.70
     Cause
    -0.69
    aminer
    -0.68
    Reviewer
    -0.67
    gee
    -0.67
    ackle
    -0.65
    POSITIVE LOGITS
     qualified
    0.93
     fled
    0.87
     clothed
    0.86
     exting
    0.83
     immersed
    0.82
     transitioned
    0.81
    rehensive
    0.80
    qualified
    0.80
     adequate
    0.79
     equipped
    0.78
    Act Density 0.009%

    No Known Activations