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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and function definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Computes
    -0.16
     Wire
    -0.15
     Gad
    -0.15
     ↵↵
    -0.15
     Marin
    -0.14
     Foo
    -0.14
     Mayo
    -0.14
     eskort
    -0.14
     Lud
    -0.13
     MBA
    -0.13
    POSITIVE LOGITS
    isContained
    0.17
    quina
    0.17
    onder
    0.15
    atrib
    0.15
    rosso
    0.15
    antz
    0.14
    objects
    0.14
    éŀ
    0.14
    indsay
    0.14
    efs
    0.14
    Act Density 0.195%

    No Known Activations