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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that indicate conditions, negations, or logical constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Hentet
    -0.86
     članak
    -0.76
    MLLoader
    -0.74
     onCreateView
    -0.67
    odiment
    -0.66
    cyjny
    -0.64
    PreferredItem
    -0.64
     Autorizaciones
    -0.63
    enterOuterAlt
    -0.63
    cyjna
    -0.62
    POSITIVE LOGITS
    enumi
    0.64
    tably
    0.62
     Reſ
    0.61
    Jereo
    0.59
    aka
    0.59
     Waray
    0.59
    at
    0.57
     mừng
    0.56
     كومونز
    0.56
    middels
    0.56
    Act Density 0.322%

    No Known Activations