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

    Neuronpedia

    INDEX
    Explanations

    references to spokespersons and their statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .want
    -0.17
    agus
    -0.17
    ongan
    -0.16
    ož
    -0.16
    aina
    -0.15
    gre
    -0.14
    isay
    -0.14
    ume
    -0.14
    udio
    -0.14
    stroy
    -0.14
    POSITIVE LOGITS
    ird
    0.15
    emsp
    0.14
    221
    0.14
    alom
    0.14
    emic
    0.14
    STRU
    0.14
    named
    0.14
    incy
    0.13
    zi
    0.13
    emie
    0.13
    Act Density 0.006%

    No Known Activations