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

    Neuronpedia

    INDEX
    Explanations

    specific names and titles related to individuals in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bsites
    -0.15
    ầm
    -0.14
    ouver
    -0.14
     bitte
    -0.14
     voks
    -0.14
    jeme
    -0.14
    punk
    -0.14
    ĵåIJį
    -0.14
    minute
    -0.14
    undos
    -0.14
    POSITIVE LOGITS
    enh
    0.14
    ysi
    0.14
    ViewSet
    0.13
    ema
    0.13
     ener
    0.13
    itag
    0.13
     ham
    0.13
    eral
    0.13
    OLT
    0.13
    æĭ¼
    0.13
    Act Density 0.043%

    No Known Activations