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

    Neuronpedia

    INDEX
    Explanations

    phrases related to academic publications and significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è·
    -0.18
    arth
    -0.16
    ãĥķãĥĪ
    -0.15
    phants
    -0.15
    viron
    -0.14
    /history
    -0.13
    raf
    -0.13
    mination
    -0.13
    виÑĩ
    -0.13
    ÌĨ
    -0.13
    POSITIVE LOGITS
    inton
    0.15
    NamedQuery
    0.15
    icot
    0.15
    -Sah
    0.14
     Bren
    0.14
     apro
    0.14
    $MESS
    0.14
    azo
    0.14
    PressEvent
    0.14
    ↵↵
    0.14
    Act Density 0.015%

    No Known Activations