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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and phrases indicating contrast or addition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .hs
    -0.15
    omap
    -0.15
    @brief
    -0.14
    iras
    -0.14
    kara
    -0.14
    utomation
    -0.14
    podob
    -0.14
     loa
    -0.13
    specifier
    -0.13
    aits
    -0.13
    POSITIVE LOGITS
     everything
    0.26
     various
    0.22
    everything
    0.21
     ranging
    0.20
    :↵
    0.20
    :
    0.19
    åIJĦç§į
    0.19
    :*
    0.17
     amongst
    0.17
    :↵↵
    0.17
    Act Density 0.002%

    No Known Activations