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

    Neuronpedia

    INDEX
    Explanations

    references to wastefulness or inefficacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rav
    -0.17
    elsius
    -0.15
     Introduced
    -0.15
    ilestone
    -0.14
    ewise
    -0.14
    浦
    -0.14
     Pew
    -0.14
     Cond
    -0.14
    rone
    -0.14
     conditional
    -0.13
    POSITIVE LOGITS
     Goldberg
    0.18
    inet
    0.16
    íĭ±
    0.15
    iker
    0.15
     Michaels
    0.15
    inct
    0.14
    :first
    0.14
    kus
    0.14
    Å¡t
    0.14
    ort
    0.14
    Act Density 0.106%

    No Known Activations