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

    Neuronpedia

    INDEX
    Explanations

    references to older siblings or relatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eling
    -0.16
    dden
    -0.15
    hem
    -0.15
    eki
    -0.15
    sono
    -0.14
    elin
    -0.14
    uong
    -0.14
     hem
    -0.14
    etic
    -0.14
    ansen
    -0.14
    POSITIVE LOGITS
    -fashioned
    0.16
    verture
    0.14
    beros
    0.14
    ÛĮرÛĮ
    0.14
    QN
    0.14
    most
    0.14
    ofilm
    0.14
    ledge
    0.13
    rió
    0.13
     ones
    0.13
    Act Density 0.018%

    No Known Activations