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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating causality or conditions

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

    the phrase "due to" at the beginning of causal explanations.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    NewUrlParser
    -0.44
    entgen
    -0.37
    zzar
    -0.37
    ější
    -0.37
     Défense
    -0.36
    nya
    -0.34
    ActiveRecord
    -0.33
    massa
    -0.33
    spir
    -0.33
    商品説明
    -0.32
    POSITIVE LOGITS
     diligence
    0.74
     '\\;'
    0.61
    OGND
    0.58
    ImageContext
    0.58
    DockStyle
    0.56
     DUE
    0.55
    Personensuche
    0.54
    ValueStyle
    0.53
    DUE
    0.53
     autorytatywna
    0.52
    Act Density 0.081%

    No Known Activations