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

    Neuronpedia

    INDEX
    Explanations

    words related to emotions or sentiments of varying intensity

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "mo," likely looking for references to emotions or mood-related speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interstitial
    -0.73
     ire
    -0.71
     Integrity
    -0.64
    ICLE
    -0.62
    rating
    -0.59
    stood
    -0.58
    AMS
    -0.58
     caution
    -0.58
     responsibility
    -0.57
     AAP
    -0.57
    POSITIVE LOGITS
    ovies
    0.96
    ogle
    0.94
    zilla
    0.91
    ose
    0.89
    aned
    0.89
    orthy
    0.87
    obil
    0.87
    edia
    0.86
    xon
    0.84
    asters
    0.84
    Act Density 0.019%

    No Known Activations