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

    Neuronpedia

    INDEX
    Explanations

    words related to sudden and rapid increases or movements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "meeting" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wisdom
    -0.65
     horror
    -0.60
     Crimes
    -0.58
     Eye
    -0.58
    JS
    -0.55
     nose
    -0.55
     CA
    -0.54
     CB
    -0.54
     sense
    -0.54
     finger
    -0.53
    POSITIVE LOGITS
    eting
    4.74
    ets
    2.08
    eters
    1.89
    etting
    1.67
    et
    1.64
    ete
    1.48
    ETS
    1.41
    etition
    1.38
    etry
    1.35
    etary
    1.34
    Act Density 0.015%

    No Known Activations