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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technology and information dissemination

    oai_token-act-pair · gpt-3.5-turbo

    symbols or characters that are likely part of a specific encoding or text format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.73
     Samar
    -0.71
     staggered
    -0.68
    itably
    -0.63
     prol
    -0.63
     eleph
    -0.62
     rotating
    -0.62
    anwhile
    -0.61
    ideon
    -0.61
     Triangle
    -0.60
    POSITIVE LOGITS
    ¹
    1.04
    į
    1.00
    º
    0.98
    £
    0.96
    ¬
    0.90
    ¼
    0.88
    ¡
    0.88
    âĢł
    0.86
    Į
    0.86
    ¥
    0.85
    Act Density 0.639%

    No Known Activations