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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    522
    -0.15
    526
    -0.15
    ãĤ¾
    -0.14
    ginas
    -0.14
    emen
    -0.14
    åŀĤ
    -0.14
    EventListener
    -0.13
    ]âĢı
    -0.13
     Innoc
    -0.13
    lä
    -0.13
    POSITIVE LOGITS
    ells
    0.16
    pra
    0.15
    ault
    0.14
    disconnect
    0.14
    elsen
    0.14
    edis
    0.14
    lever
    0.14
    uth
    0.13
     Shapiro
    0.13
     Moran
    0.13
    Act Density 0.341%

    No Known Activations