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

    Neuronpedia

    INDEX
    Explanations

    emphatic statements or exclamations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uto
    -0.14
    verty
    -0.14
    jej
    -0.14
    yte
    -0.14
    formance
    -0.14
    enberg
    -0.13
    APE
    -0.13
    ushman
    -0.13
    .Hand
    -0.13
    .gs
    -0.13
    POSITIVE LOGITS
    sted
    0.16
    ————————————————
    0.15
    گاÙĨ
    0.14
    妮
    0.14
    گاÙĨÛĮ
    0.14
    Ä°SÄ°
    0.14
     CONTRACT
    0.13
     Cater
    0.13
    WithError
    0.13
    endar
    0.13
    Act Density 0.036%

    No Known Activations