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

    Neuronpedia

    INDEX
    Explanations

    technical phrases related to software configuration and settings

    oai_token-act-pair · gpt-3.5-turbo

    terms related to configuration settings and management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.85
    cart
    -0.82
    liam
    -0.82
    past
    -0.82
    bery
    -0.79
    icz
    -0.79
    manship
    -0.75
    Girls
    -0.73
    borough
    -0.71
    cott
    -0.70
    POSITIVE LOGITS
    uration
    1.37
    urations
    1.36
    urable
    1.19
    urated
    0.86
     configuration
    0.86
     file
    0.86
     variables
    0.83
     parameters
    0.83
     configurations
    0.83
     logger
    0.79
    Act Density 0.030%

    No Known Activations