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

    Neuronpedia

    INDEX
    Explanations

    special characters and formatting codes within the text

    oai_token-act-pair · gpt-3.5-turbo

    characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     strikers
    -0.71
    istics
    -0.71
    auder
    -0.70
    stri
    -0.69
    versions
    -0.68
    psey
    -0.68
    involved
    -0.67
    eneg
    -0.67
     nomine
    -0.66
     endings
    -0.66
    POSITIVE LOGITS
    ·
    1.34
    °
    1.32
    ¸
    1.28
    ¾
    1.22
    ¼
    1.19
    ½
    1.17
    µ
    1.15
    ı
    1.13
    ´
    1.12
    Ö¼
    1.06
    Act Density 0.005%

    No Known Activations