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

    Neuronpedia

    INDEX
    Explanations

    Cyrillic script characters

    oai_token-act-pair · gpt-4-turbo

    characters in different languages

    oai_token-act-pair · gpt-3.5-turbo

    special characters or non-standard symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ORED
    -0.82
    aday
    -0.75
     Starr
    -0.68
     guiActiveUnfocused
    -0.67
    orkshire
    -0.66
    ocrine
    -0.63
    hof
    -0.63
    espie
    -0.61
    wagen
    -0.60
     Heath
    -0.60
    POSITIVE LOGITS
     Ð
    1.32
    ¾
    1.29
    ľ
    1.23
    ł
    1.22
    ¼
    1.22
    ļ
    1.22
    ½
    1.21
    Ķ
    1.21
    ķ
    1.19
    ij
    1.18
    Act Density 0.005%

    No Known Activations