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

    Neuronpedia

    INDEX
    Explanations

    instances of deception or trickery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itative
    -0.15
    uttle
    -0.15
    itung
    -0.14
     ApplicationException
    -0.14
    tdown
    -0.14
    otate
    -0.14
    hower
    -0.14
    768
    -0.14
     forg
    -0.14
    .hp
    -0.14
    POSITIVE LOGITS
    icers
    0.14
     dynamic
    0.14
     Mart
    0.13
    Dynamic
    0.13
    amente
    0.13
     Barrier
    0.13
     Dynamic
    0.13
    aison
    0.13
     skirt
    0.13
    ÑĩеÑĤ
    0.13
    Act Density 0.039%

    No Known Activations