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

    Neuronpedia

    INDEX
    Explanations

    phrases with unique characters like "ç" and "ÅŁ"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character "ç."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Breed
    -0.71
     mileage
    -0.67
     benefic
    -0.67
     rooting
    -0.66
     mutual
    -0.65
     trail
    -0.63
     compuls
    -0.62
     marrow
    -0.62
    OSP
    -0.61
    ACTED
    -0.60
    POSITIVE LOGITS
    ão
    1.25
    ç
    1.06
    ã
    1.03
    uration
    0.96
    arta
    0.96
    onne
    0.94
    án
    0.91
    ü
    0.88
    ĩ
    0.88
    ón
    0.87
    Act Density 0.006%

    No Known Activations