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

    Neuronpedia

    INDEX
    Explanations

    questions and discussions around technical issues or missing features in software

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ChildScrollView
    -0.43
     relev
    -0.42
    Werdegang
    -0.42
     flash
    -0.40
     accompanied
    -0.38
     next
    -0.38
     assisted
    -0.37
     plate
    -0.37
    ✨:
    -0.37
    '][]
    -0.36
    POSITIVE LOGITS
     Absence
    0.61
     lacking
    0.59
     lack
    0.58
    Absence
    0.57
     absence
    0.56
    SharedCtor
    0.56
     Lack
    0.55
    Lack
    0.54
    absence
    0.54
     отсутствие
    0.54
    Act Density 0.800%

    No Known Activations