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

    Neuronpedia

    INDEX
    Explanations

    instances of quotation marks and references to speech or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æk
    -0.15
    ringe
    -0.15
     iParam
    -0.15
    orque
    -0.14
    idot
    -0.14
    aways
    -0.14
    BIN
    -0.14
    sass
    -0.14
    éı¡
    -0.14
    rames
    -0.14
    POSITIVE LOGITS
    era
    0.18
    ÂĿ
    0.16
    eros
    0.15
    лика
    0.14
     Fog
    0.14
    ernity
    0.14
    boy
    0.13
     Bas
    0.13
    chl
    0.13
    nx
    0.13
    Act Density 0.010%

    No Known Activations