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

    Neuronpedia

    INDEX
    Explanations

    significant terms or phrases indicating conditions or criteria that require careful consideration or evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iaux
    -0.19
    andle
    -0.18
    vik
    -0.17
    ANDLE
    -0.15
    yre
    -0.15
    .Abs
    -0.15
    orre
    -0.15
    ayet
    -0.14
    holm
    -0.14
    ssp
    -0.14
    POSITIVE LOGITS
     den
    0.14
     warm
    0.14
     staples
    0.14
     Pen
    0.14
     mass
    0.14
    udiant
    0.14
     tro
    0.14
    atre
    0.13
    Pen
    0.13
    adora
    0.13
    Act Density 0.001%

    No Known Activations