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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and their frequency of occurrence in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fubject
    -0.63
     tranſ
    -0.57
     ſtate
    -0.54
     purpoſe
    -0.53
    ſelf
    -0.52
     ſta
    -0.52
     itſelf
    -0.52
     ſon
    -0.51
     ſtand
    -0.50
     ſtre
    -0.50
    POSITIVE LOGITS
     I
    0.54
     if
    0.48
     it
    0.48
     وتسجيلات
    0.48
     you
    0.47
    UnitTesting
    0.42
    ogy
    0.42
    pyx
    0.42
     BAM
    0.41
     we
    0.41
    Act Density 0.353%

    No Known Activations