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

    Neuronpedia

    INDEX
    Explanations

    words related to countries and locations

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'y' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     exha
    -0.60
    ĭ
    -0.58
    eline
    -0.57
    ocol
    -0.57
    ĸ
    -0.57
    ª
    -0.57
    ãĤ½
    -0.57
    andum
    -0.54
    âĸĪâĸĪ
    -0.54
    »
    -0.54
    POSITIVE LOGITS
    wagen
    0.60
    nexus
    0.60
    sburg
    0.57
    cham
    0.55
     celebrates
    0.54
    alian
    0.53
    sterdam
    0.53
    cape
    0.52
    auga
    0.51
     legalized
    0.51
    Act Density 0.751%

    No Known Activations