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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a time reference from the past

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "long before."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wich
    -0.72
    gallery
    -0.70
    atic
    -0.69
    ¸
    -0.68
    arse
    -0.68
    dale
    -0.68
    cheat
    -0.68
    âĵĺ
    -0.67
    ield
    -0.67
    <?
    -0.67
    POSITIVE LOGITS
     anyone
    1.10
     anybody
    0.99
     any
    0.91
     anything
    0.88
     ANY
    0.83
     existed
    0.79
     Gutenberg
    0.73
     advent
    0.72
     neocons
    0.71
     mattered
    0.71
    Act Density 0.086%

    No Known Activations