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

    Neuronpedia

    INDEX
    Explanations

    instances of structural or formatting elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     تانيه
    -0.94
    wnętr
    -0.76
    Дереккөздер
    -0.72
     Cæsar
    -0.71
     Kraus
    -0.68
    uks
    -0.68
    exao
    -0.68
     yawn
    -0.67
    MigrationBuilder
    -0.67
     käytet
    -0.67
    POSITIVE LOGITS
    ating
    0.81
    izing
    0.75
    ting
    0.73
     taking
    0.72
     doing
    0.67
     transporting
    0.66
    fying
    0.63
     making
    0.63
    paying
    0.62
     paying
    0.62
    Act Density 0.299%

    No Known Activations