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

    Neuronpedia

    INDEX
    Explanations

    phrases and expressions related to personal beliefs and opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eut
    -0.16
    urance
    -0.15
    ISCO
    -0.15
    ayi
    -0.15
    eur
    -0.15
    ollower
    -0.14
    æĺĩ
    -0.14
    streams
    -0.14
    oyer
    -0.14
    ylland
    -0.14
    POSITIVE LOGITS
    eti
    0.17
    otti
    0.15
    155
    0.15
    790
    0.15
    ASH
    0.14
    athan
    0.14
    ibar
    0.14
    abh
    0.13
    393
    0.13
    chia
    0.13
    Act Density 0.082%

    No Known Activations