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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names, specifically with the pattern of a person's first name followed by their last name

    oai_token-act-pair · gpt-3.5-turbo

    the word "one" and its variations, suggesting a focus on singularity or individualism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     actionGroup
    -0.79
    lished
    -0.71
    æĸ¹
    -0.71
    NRS
    -0.70
     resil
    -0.67
    hips
    -0.66
     precip
    -0.65
     brig
    -0.62
     subp
    -0.61
    orsi
    -0.59
    POSITIVE LOGITS
    xus
    0.89
    gger
    0.88
    xit
    0.86
    ones
    0.79
    hoe
    0.79
    boarding
    0.78
    Voice
    0.76
     Hundred
    0.76
    esan
    0.75
    ciating
    0.75
    Act Density 0.020%

    No Known Activations