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

    Neuronpedia

    INDEX
    Explanations

    emotionally charged verbs related to surprise or shock

    oai_token-act-pair · gpt-3.5-turbo

    words and expressions indicating strong emotional reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascript
    -0.72
     slips
    -0.71
    itions
    -0.66
     indexed
    -0.62
    aneous
    -0.61
    pointer
    -0.59
     polymorph
    -0.58
     organizing
    -0.57
    ãĥ¼ãĥ³
    -0.56
     arsen
    -0.56
    POSITIVE LOGITS
     us
    0.90
     me
    0.85
     him
    0.85
     everybody
    0.78
     them
    0.75
     everyone
    0.74
     anybody
    0.70
     onlook
    0.69
     Beir
    0.69
    HOU
    0.66
    Act Density 0.162%

    No Known Activations