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

    Neuronpedia

    INDEX
    Explanations

    words related to the central or most important part of something

    oai_token-act-pair · gpt-3.5-turbo

    the term "core" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.81
    hops
    -0.72
    TN
    -0.67
    chedel
    -0.66
    _-
    -0.65
    channelAvailability
    -0.62
    OTO
    -0.62
    Pause
    -0.62
    ija
    -0.62
    ã
    -0.62
    POSITIVE LOGITS
    xit
    0.95
    opsis
    0.92
    stone
    0.86
     core
    0.83
    lig
    0.82
     essence
    0.81
     tenets
    0.79
    most
    0.79
    edly
    0.78
    utils
    0.76
    Act Density 0.013%

    No Known Activations