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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÃŃ
    -0.15
    ÄĻ
    -0.15
    empl
    -0.14
    ãģ°ãģĭãĤĬ
    -0.13
    rame
    -0.13
     atan
    -0.13
    éĥ¡
    -0.13
    231
    -0.13
     o
    -0.12
    otre
    -0.12
    POSITIVE LOGITS
    ÅŁi
    0.15
    ESSAGES
    0.15
     Bilim
    0.15
    atz
    0.15
    ylv
    0.15
    uales
    0.14
    .analytics
    0.14
    ovna
    0.14
     shock
    0.14
    ainted
    0.14
    Act Density 0.416%

    No Known Activations