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

    Neuronpedia

    INDEX
    Explanations

    terms related to philosophical or academic discussions around theories and concepts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     intersper
    -1.15
     reluct
    -1.04
     unspeak
    -1.04
     shenan
    -0.96
     intrigu
    -0.95
     sophistic
    -0.95
     disagre
    -0.93
     apprehen
    -0.92
     indestru
    -0.92
     philanth
    -0.90
    POSITIVE LOGITS
     assume
    0.62
     overlook
    0.61
     insuffisamment
    0.61
     ignore
    0.61
     overlooks
    0.60
     overlooking
    0.59
     focus
    0.57
     ignores
    0.55
     assumptions
    0.55
    enderror
    0.54
    Act Density 0.561%

    No Known Activations