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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating an accumulation of negative experiences or challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çľ
    -0.16
    اÙģت
    -0.15
    826
    -0.14
    mpp
    -0.14
    982
    -0.14
    æ¤į
    -0.14
    Ñīи
    -0.14
    ylan
    -0.14
    pink
    -0.14
    ugg
    -0.13
    POSITIVE LOGITS
     icing
    0.27
     iceberg
    0.23
     proverb
    0.22
     insult
    0.21
     cake
    0.20
     cherry
    0.20
     straw
    0.19
    icing
    0.19
     tip
    0.18
     Straw
    0.16
    Act Density 0.095%

    No Known Activations