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

    Neuronpedia

    INDEX
    Explanations

    French terms related to specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "Le" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģĨ
    -0.97
    ãĥ¼ãĥĨ
    -0.90
    ividual
    -0.89
    aneers
    -0.89
    acca
    -0.88
    ħĭ
    -0.87
     teasp
    -0.85
    MODE
    -0.83
    iosyncr
    -0.79
    ĸļ
    -0.77
    POSITIVE LOGITS
    icester
    1.15
    isure
    1.01
    opard
    0.93
    ttes
    0.91
    Bron
    0.89
    lean
    0.88
    agues
    0.88
    ague
    0.86
    lla
    0.85
    ather
    0.81
    Act Density 0.005%

    No Known Activations