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

    Neuronpedia

    INDEX
    Explanations

    references to various media publications and their reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tale
    -0.17
     Herb
    -0.16
    past
    -0.15
    halt
    -0.15
     mænd
    -0.14
     Lexer
    -0.14
    ünst
    -0.14
     wik
    -0.14
    _RESOLUTION
    -0.14
    ubre
    -0.14
    POSITIVE LOGITS
     daily
    0.20
     Gong
    0.19
     newspaper
    0.18
     Newspaper
    0.18
    osphere
    0.17
     broad
    0.17
     RTL
    0.17
     Express
    0.16
     panorama
    0.16
     EXPRESS
    0.16
    Act Density 0.088%

    No Known Activations