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

    Neuronpedia

    INDEX
    Explanations

    contractions and possessive forms

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odium
    -0.62
     Yor
    -0.62
     Palest
    -0.61
    Buyable
    -0.60
    èĢħ
    -0.60
     Crush
    -0.59
     aspir
    -0.57
     Commodore
    -0.56
     Alto
    -0.56
     Codec
    -0.56
    POSITIVE LOGITS
    s
    0.83
    ves
    0.80
    \\\\\\\\
    0.79
    ve
    0.77
    re
    0.73
    cker
    0.73
    been
    0.72
    \'
    0.72
    ����
    0.72
    plays
    0.71
    Act Density 0.229%

    No Known Activations