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

    Neuronpedia

    INDEX
    Explanations

    phrases or elements marked with special symbols like âĢĵ

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific character or symbol across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.73
    orts
    -0.71
    pell
    -0.69
    ysis
    -0.69
    odcast
    -0.67
    ient
    -0.67
    zbek
    -0.66
    zhou
    -0.66
     extingu
    -0.65
    pping
    -0.64
    POSITIVE LOGITS
    ––
    1.28
    âĸº
    0.96
    _-
    0.88
    ————
    0.80
    Maria
    0.77
    Tenn
    0.73
    Britain
    0.73
    perhaps
    0.72
    ————————————————
    0.72
    =-=-
    0.71
    Act Density 0.121%

    No Known Activations