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

    Neuronpedia

    INDEX
    Explanations

    elements related to compliance and evaluation criteria in formal documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onical
    -0.17
    برÛĮ
    -0.14
    º
    -0.14
    .onViewCreated
    -0.14
    .nih
    -0.13
    ιαÏĤ
    -0.13
    jang
    -0.13
    aeda
    -0.13
    ovat
    -0.13
    REFERRED
    -0.13
    POSITIVE LOGITS
     check
    0.71
     tick
    0.70
     checked
    0.66
    check
    0.60
     Tick
    0.58
     Check
    0.57
     CHECK
    0.57
     ticks
    0.56
     checking
    0.55
    tick
    0.55
    Act Density 0.140%

    No Known Activations