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

    Neuronpedia

    INDEX
    Explanations

    conversational fillers or discourse markers used to express surprise, uncertainty, or hesitation

    oai_token-act-pair · gpt-3.5-turbo

    rhetorical questions and expressions of surprise or curiosity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iors
    -0.69
    irie
    -0.68
    iple
    -0.68
    upiter
    -0.67
    uci
    -0.65
     guiActiveUnfocused
    -0.65
    ument
    -0.65
    edom
    -0.64
    escription
    -0.63
    enaries
    -0.63
    POSITIVE LOGITS
     huh
    1.22
     considering
    1.17
     eh
    1.04
    especially
    0.99
     especially
    0.99
     but
    0.94
    but
    0.90
     Especially
    0.87
     frankly
    0.84
     given
    0.82
    Act Density 0.198%

    No Known Activations