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

    Neuronpedia

    INDEX
    Explanations

    configurations or settings mentioned in technical contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "config" and its variants related to configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.94
     Gael
    -0.76
    bery
    -0.75
    soever
    -0.72
    âĹ¼
    -0.71
    Downloadha
    -0.71
    FORE
    -0.69
     Apost
    -0.68
    birth
    -0.66
     polio
    -0.65
    POSITIVE LOGITS
    uration
    1.57
    urations
    1.56
    urable
    1.38
    urated
    1.09
    ured
    1.04
    uring
    1.01
    urer
    0.98
    anooga
    0.98
    Parser
    0.93
    config
    0.92
    Act Density 0.009%

    No Known Activations