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

    Neuronpedia

    INDEX
    Explanations

    the beginning of sentences or paragraphs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ly
    -0.72
    imal
    -0.66
     versus
    -0.63
    CodeAttribute
    -0.62
    LY
    -0.62
    DataMap
    -0.62
    mbra
    -0.62
    サイ
    -0.61
    este
    -0.60
    ),),
    -0.58
    POSITIVE LOGITS
     bakgrund
    0.87
     détru
    0.84
     Devonian
    0.80
     varandra
    0.78
     prêtres
    0.77
     înal
    0.76
     itſelf
    0.76
     papild
    0.76
     religieuses
    0.75
     مشين
    0.75
    Act Density 0.052%

    No Known Activations