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

    Neuronpedia

    INDEX
    Explanations

    references to citizenship and community engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ieri
    -0.16
    lesia
    -0.15
    pees
    -0.15
    geb
    -0.15
    itra
    -0.15
     './../
    -0.15
    ogui
    -0.14
    丸
    -0.14
    nothrow
    -0.14
    gles
    -0.14
    POSITIVE LOGITS
     whom
    0.18
     whose
    0.16
    lius
    0.15
    hoo
    0.15
    ecz
    0.14
     Brow
    0.14
    847
    0.14
    etic
    0.14
    /topics
    0.13
     who
    0.13
    Act Density 0.918%

    No Known Activations