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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating directions or references to additional information and resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yre
    -0.17
    olle
    -0.16
    errick
    -0.15
    alars
    -0.15
    olo
    -0.15
    olley
    -0.14
    ettle
    -0.14
    оло
    -0.14
    à¹Ĥà¸Ĭ
    -0.14
    assi
    -0.14
    POSITIVE LOGITS
    zos
    0.17
    orp
    0.16
    iot
    0.15
    apos
    0.14
     Hobby
    0.14
    ¼
    0.14
    oksen
    0.14
    infinity
    0.14
    Neutral
    0.14
    opes
    0.13
    Act Density 0.449%

    No Known Activations