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

    Neuronpedia

    INDEX
    Explanations

    references to "first time" experiences or events

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

    first time experiences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betrek
    -0.49
     henvis
    -0.44
    attutto
    -0.43
     escenas
    -0.43
     gruesa
    -0.43
    ジェクト
    -0.42
     strijd
    -0.42
     invloed
    -0.42
     voedsel
    -0.42
     serpiente
    -0.41
    POSITIVE LOGITS
     مشين
    0.70
    !*\
    0.60
    OGND
    0.59
    ########.
    0.59
    NameInMap
    0.59
     ***!
    0.56
     autorytatywna
    0.55
    Personensuche
    0.53
    第一次
    0.52
    GEBURTS
    0.51
    Act Density 0.005%

    No Known Activations