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

    Neuronpedia

    INDEX
    Explanations

    phrases related to equalizing or improving access to various services and resources

    oai_token-act-pair · gpt-3.5-turbo

    references to access to various resources and services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kern
    -0.79
    Maker
    -0.63
     Fenrir
    -0.62
    mac
    -0.62
    warm
    -0.62
     Saud
    -0.61
    thin
    -0.61
    dylib
    -0.60
     Opera
    -0.60
    rob
    -0.60
    POSITIVE LOGITS
    ibility
    1.28
    ibly
    1.22
    ible
    1.07
    ibles
    1.05
    ibilities
    0.98
     access
    0.89
    ion
    0.88
    ioned
    0.85
    ibl
    0.82
    ãĥ¼ãĥĨ
    0.82
    Act Density 0.020%

    No Known Activations