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

    Neuronpedia

    INDEX
    Explanations

    information related to tragic real-life events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     anecd
    -0.84
    pmwiki
    -0.74
     inconsist
    -0.73
     overlap
    -0.73
     notably
    -0.71
     biases
    -0.70
     egreg
    -0.68
     overlapping
    -0.67
     whiff
    -0.65
     Notably
    -0.64
    POSITIVE LOGITS
     someday
    1.30
    thood
    1.01
     afterlife
    0.93
     repay
    0.88
     revenge
    0.86
     immortality
    0.85
     eternity
    0.79
     hereafter
    0.78
    venge
    0.77
     repent
    0.75
    Act Density 0.753%

    No Known Activations