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

    Neuronpedia

    INDEX
    Explanations

    terms related to tokens or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Савезне
    -0.92
     تانيه
    -0.78
     للمعارف
    -0.74
     متعلقه
    -0.71
    Referanser
    -0.69
     >=",
    -0.64
     Paglinawan
    -0.63
    IndentedString
    -0.63
    idopsis
    -0.62
     يتيمه
    -0.58
    POSITIVE LOGITS
     is
    0.91
     has
    0.80
     also
    0.77
     itself
    0.66
     only
    0.64
     She
    0.63
     will
    0.63
     them
    0.60
     definitely
    0.59
     neither
    0.58
    Act Density 0.433%

    No Known Activations