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

    Neuronpedia

    INDEX
    Explanations

    words related to speaking or communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ildo
    -0.18
    readcr
    -0.17
    rien
    -0.15
    ecycle
    -0.15
    aki
    -0.15
    /out
    -0.14
    물
    -0.14
     Hawth
    -0.14
    igation
    -0.14
    bane
    -0.14
    POSITIVE LOGITS
    peare
    0.17
    erville
    0.16
    neider
    0.16
    izoph
    0.15
    ONS
    0.15
    reau
    0.14
    ake
    0.14
    /sign
    0.14
    /write
    0.14
    ooled
    0.14
    Act Density 0.048%

    No Known Activations