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

    Neuronpedia

    INDEX
    Explanations

    adverbs describing the extent or manner of an action or event

    oai_token-act-pair · gpt-3.5-turbo

    words that indicate visible or noticeable emotional states or reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    berman
    -0.84
    zsche
    -0.80
    claimer
    -0.68
    ridge
    -0.68
    quote
    -0.67
    directed
    -0.67
    spr
    -0.65
    cius
    -0.65
    enthal
    -0.64
    pez
    -0.64
    POSITIVE LOGITS
     noticeable
    1.00
     audible
    0.90
     detectable
    0.79
    Flor
    0.74
     Dull
    0.72
     visible
    0.72
     defic
    0.72
    Ju
    0.72
     percept
    0.71
     noticeably
    0.71
    Act Density 0.019%

    No Known Activations