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

    Neuronpedia

    INDEX
    Explanations

    exclamatory or impactful words and phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to explosive sounds or impactful events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Immun
    -0.70
    ser
    -0.68
    authorized
    -0.64
    Ser
    -0.64
     Hist
    -0.64
     Courage
    -0.64
     Waters
    -0.63
    aut
    -0.62
     Chart
    -0.61
     Participant
    -0.60
    POSITIVE LOGITS
     bang
    4.54
    bang
    2.73
     Bang
    1.70
     banging
    1.66
    Bang
    1.56
     bust
    0.98
     boom
    0.95
     busted
    0.93
     smack
    0.92
     slam
    0.91
    Act Density 0.013%

    No Known Activations