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

    Neuronpedia

    INDEX
    Explanations

    sentences ending with specific formatting symbols

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific symbol sequences or patterns represented by "âĢ"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wagen
    -0.71
     Samar
    -0.70
     multiplying
    -0.69
     touches
    -0.67
    nesday
    -0.66
     municipality
    -0.65
     multiplied
    -0.65
     furthe
    -0.63
     shroud
    -0.63
    abwe
    -0.62
    POSITIVE LOGITS
    £
    1.14
    º
    1.13
    ¹
    1.07
    ¡
    1.04
    »
    1.02
    ®
    1.02
    ¬
    1.00
    Į
    0.98
    ł
    0.98
    ľ
    0.97
    Act Density 0.138%

    No Known Activations