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

    Neuronpedia

    INDEX
    Explanations

    words related to the context in which something occurs

    oai_token-act-pair · gpt-3.5-turbo

    references to context in discussions or explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    STON
    -0.83
    vals
    -0.73
    owship
    -0.70
    deen
    -0.69
    ãĥīãĥ©
    -0.66
    doms
    -0.66
    riage
    -0.66
    chens
    -0.65
    aliation
    -0.65
    aah
    -0.65
    POSITIVE LOGITS
     context
    0.95
    ually
    0.93
    ual
    0.89
    uality
    0.84
     contexts
    0.80
     Context
    0.76
     menus
    0.73
     contextual
    0.72
     menu
    0.72
    forward
    0.70
    Act Density 0.025%

    No Known Activations