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

    Neuronpedia

    INDEX
    Explanations

    words related to spontaneity and unplanned events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "spontaneous" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adr
    -0.82
     Advocate
    -0.77
     Fighting
    -0.72
    aneers
    -0.69
    urden
    -0.68
    iasis
    -0.66
    orney
    -0.66
    wives
    -0.66
    èª
    -0.65
    mis
    -0.65
    POSITIVE LOGITS
    aneous
    1.22
     combustion
    1.11
    aneously
    1.10
     spontaneous
    1.02
     combust
    1.00
     spontaneously
    0.89
     pandemonium
    0.86
     laughter
    0.80
     unle
    0.80
     outburst
    0.78
    Act Density 0.010%

    No Known Activations