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

    Neuronpedia

    INDEX
    Explanations

    references to bonuses or additional features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ugo
    -0.16
    121
    -0.15
    988
    -0.15
    atis
    -0.15
    NET
    -0.15
    èĤĥ
    -0.15
     Au
    -0.14
    ÙĤØ·
    -0.14
    bach
    -0.14
    OTS
    -0.14
    POSITIVE LOGITS
    ispers
    0.15
    да
    0.15
    hon
    0.14
     Corner
    0.14
    endum
    0.14
     seksi
    0.13
    lea
    0.13
     viel
    0.13
     bonus
    0.13
    aths
    0.13
    Act Density 0.259%

    No Known Activations