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

    Neuronpedia

    INDEX
    Explanations

    questions or statements regarding hypothetical situations or predictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uters
    -0.16
    ipur
    -0.15
    ácil
    -0.14
    abra
    -0.14
    ibbon
    -0.14
    ainer
    -0.14
    iesz
    -0.14
    iets
    -0.14
     disruptive
    -0.14
     pon
    -0.13
    POSITIVE LOGITS
    orr
    0.16
    è¹
    0.15
    endale
    0.15
    OutOfBounds
    0.15
    acre
    0.14
    ahl
    0.14
    ,['
    0.14
    SPATH
    0.14
    æ²ī
    0.14
    ylon
    0.14
    Act Density 0.112%

    No Known Activations