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

    Neuronpedia

    INDEX
    Explanations

    strings of characters that appear to be a mix of letters, numbers, and symbols

    oai_token-act-pair · gpt-3.5-turbo

    specific accented or special characters in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rooting
    -0.74
     stake
    -0.71
     marrow
    -0.69
     queens
    -0.67
    iqueness
    -0.66
     miss
    -0.64
     bearer
    -0.63
     disemb
    -0.62
     Coliseum
    -0.62
    ModLoader
    -0.62
    POSITIVE LOGITS
    ti
    0.88
    nik
    0.86
    atar
    0.82
    ĩ
    0.80
    Ã
    0.80
    0.79
    ı
    0.79
    kil
    0.79
    dra
    0.77
    kov
    0.77
    Act Density 0.017%

    No Known Activations