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

    Neuronpedia

    INDEX
    Explanations

    specific instances of people observing events

    oai_token-act-pair · gpt-3.5-turbo

    instances of observation or experiences related to witnessing events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    este
    -0.72
    brainer
    -0.72
    quote
    -0.71
    trap
    -0.70
    lique
    -0.69
     drawer
    -0.65
    afort
    -0.65
    govtrack
    -0.65
    ayers
    -0.63
    prep
    -0.62
    POSITIVE LOGITS
     firsthand
    1.20
    ewitness
    0.92
    ĸļ
    0.77
     witnessing
    0.77
     pandemonium
    0.76
    Witness
    0.75
    Events
    0.73
     Witness
    0.71
    IDENT
    0.70
     Watching
    0.69
    Act Density 0.039%

    No Known Activations