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

    Neuronpedia

    INDEX
    Explanations

    emotional responses and evaluations related to films or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "At" followed by adverbs of time

    np_acts-logits-general · gemini-2.0-flash

    at times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.63
     ModelExpression
    -0.59
     متعلقه
    -0.57
    writeFieldEnd
    -0.56
    ViewFeatures
    -0.55
    存于互联网档案馆
    -0.55
     مشين
    -0.55
    setVerticalGroup
    -0.55
    rungsseite
    -0.54
    Geplaatst
    -0.54
    POSITIVE LOGITS
     sometimes
    1.94
    sometimes
    1.70
     parfois
    1.69
     occasionally
    1.68
     Sometimes
    1.60
    Sometimes
    1.52
     ibland
    1.52
     soms
    1.51
     иногда
    1.47
     Occasionally
    1.47
    Act Density 0.295%

    No Known Activations