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

    Neuronpedia

    INDEX
    Explanations

    numerical references or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agoon
    -0.07
    å¯Į
    -0.07
    ibri
    -0.07
    agina
    -0.07
    onds
    -0.07
    /cop
    -0.07
    abet
    -0.07
    erus
    -0.07
    å®ĩ
    -0.06
    etim
    -0.06
    POSITIVE LOGITS
    ormal
    0.06
    voy
    0.06
    udden
    0.06
    ucle
    0.06
    emann
    0.06
    314
    0.05
    uxt
    0.05
    alty
    0.05
    ORMAL
    0.05
    cheng
    0.05
    Act Density 0.002%

    No Known Activations