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

    Neuronpedia

    INDEX
    Explanations

    references to published works, such as articles and essays

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _checkout
    -0.15
    оÑĤв
    -0.15
     Bulk
    -0.14
    crollView
    -0.14
    itness
    -0.14
    Eval
    -0.14
    erals
    -0.14
    otp
    -0.13
    .AI
    -0.13
    lico
    -0.13
    POSITIVE LOGITS
     appeared
    0.87
     appearing
    0.79
     appearance
    0.75
    appeared
    0.68
     appear
    0.68
     apare
    0.68
     Appearance
    0.66
     appears
    0.65
     appearances
    0.64
    appear
    0.59
    Act Density 0.142%

    No Known Activations