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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating inclusivity or universality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.73
    LabelTagHelper
    -0.62
    strconv
    -0.60
    schedulers
    -0.59
    thenReturn
    -0.56
     resultCode
    -0.55
     основном
    -0.55
     strconv
    -0.54
    ագրություններ
    -0.54
    kkor
    -0.54
    POSITIVE LOGITS
     any
    4.37
     Any
    3.81
    Any
    3.77
    any
    3.49
     ANY
    3.47
    ANY
    3.06
     cualquier
    2.96
    任何
    2.89
     qualquer
    2.89
     qualsiasi
    2.70
    Act Density 0.110%

    No Known Activations