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

    Neuronpedia

    INDEX
    Explanations

    phrases related to composition and organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rivit
    -0.60
    saraba
    -0.54
    Personendaten
    -0.53
    abetes
    -0.45
    дивиду
    -0.44
     مشين
    -0.42
     Chaque
    -0.42
    ferous
    -0.42
    Humble
    -0.41
    Touchable
    -0.40
    POSITIVE LOGITS
     mostly
    2.65
     predominantly
    2.61
     mainly
    2.60
     primarily
    2.50
     Mostly
    2.38
    mostly
    2.36
    Mostly
    2.35
     Mainly
    2.29
    mainly
    2.20
    primarily
    2.20
    Act Density 0.737%

    No Known Activations