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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical theories and authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     åł
    -0.18
     ç·
    -0.15
    neys
    -0.15
    (es
    -0.15
    479
    -0.15
     vál
    -0.15
    íĥ
    -0.15
     IHttp
    -0.14
    loud
    -0.14
    à¤Ĥà¤ľà¤¨
    -0.14
    POSITIVE LOGITS
    ensibly
    0.19
    agma
    0.18
    opathic
    0.17
    eo
    0.17
    opor
    0.16
    hol
    0.14
    374
    0.14
    etter
    0.14
    ec
    0.14
    ensively
    0.14
    Act Density 0.016%

    No Known Activations