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

    Neuronpedia

    INDEX
    Explanations

    names of political figures, especially Emmanuel Macron

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    istani
    -0.84
    aband
    -0.81
    rawn
    -0.76
    orns
    -0.76
    arse
    -0.75
    ordinate
    -0.74
    aways
    -0.73
    tips
    -0.73
    fold
    -0.72
    anas
    -0.72
    POSITIVE LOGITS
    aukee
    0.74
    xes
    0.74
    llan
    0.73
    eor
    0.71
    oire
    0.69
    pora
    0.66
    paio
    0.66
     Harden
    0.65
    lda
    0.65
    Ö¼
    0.64
    Act Density 0.052%

    No Known Activations