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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their relationships in the content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     day
    -0.44
    ps
    -0.43
    ,
    -0.42
     rov
    -0.40
     like
    -0.40
    <
    -0.39
     Day
    -0.39
    不容
    -0.38
     i
    -0.38
     исто
    -0.38
    POSITIVE LOGITS
     مرئيه
    0.95
     виправивши
    0.93
    Tikang
    0.91
    Хьажоргаш
    0.89
     tartalomajánló
    0.84
     ffilmiau
    0.82
     bezeichneter
    0.79
    WriteBarrier
    0.77
     GetEnumerator
    0.77
    lccn
    0.74
    Act Density 0.979%

    No Known Activations