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

    Neuronpedia

    INDEX
    Explanations

    words related to disasters and catastrophic events

    oai_token-act-pair · gpt-3.5-turbo

    words related to failure or catastrophic events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    76561
    -0.71
    ourt
    -0.69
    hetical
    -0.67
    arov
    -0.65
    orney
    -0.64
    pora
    -0.63
    lean
    -0.63
    pha
    -0.62
     entertained
    -0.62
    alist
    -0.62
    POSITIVE LOGITS
     spontaneously
    1.16
     violently
    1.04
     unexpectedly
    1.03
     prematurely
    1.02
     uncontroll
    1.00
     mysteriously
    0.97
     explos
    0.96
     horribly
    0.95
     catast
    0.93
     miser
    0.91
    Act Density 0.239%

    No Known Activations