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

    Neuronpedia

    INDEX
    Explanations

    elements related to comments and posting interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hy
    -0.17
     (
    -0.17
    ember
    -0.17
    azzo
    -0.16
    erre
    -0.16
    ière
    -0.15
    erable
    -0.14
     wid
    -0.14
     learn
    -0.14
     Scout
    -0.14
    POSITIVE LOGITS
    ardon
    0.15
    avin
    0.14
     FRONT
    0.14
    hte
    0.14
    VERR
    0.14
    ç±
    0.14
    Æ°Æ¡ng
    0.14
    DataStream
    0.14
    izin
    0.14
    utherland
    0.14
    Act Density 0.030%

    No Known Activations