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

    Neuronpedia

    INDEX
    Explanations

    instances of actions or conditions that imply a significant state or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ENTA
    -0.13
     resil
    -0.13
    ços
    -0.13
    оÑĩки
    -0.13
     صÙĨع
    -0.13
    ickest
    -0.13
     åĥ
    -0.13
    .atomic
    -0.12
    _RENDERER
    -0.12
    asher
    -0.12
    POSITIVE LOGITS
    0.16
    motion
    0.14
     physical
    0.14
    inson
    0.14
    utos
    0.13
     Cater
    0.13
     warrant
    0.13
     physically
    0.13
    inux
    0.13
     motion
    0.12
    Act Density 0.071%

    No Known Activations