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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax and code components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ozem
    -0.15
     ydk
    -0.15
    addir
    -0.14
     seedu
    -0.14
    ëĿ½
    -0.14
    ui
    -0.14
    entes
    -0.13
     mÃŃn
    -0.13
    롱
    -0.13
     Äįe
    -0.13
    POSITIVE LOGITS
     >>
    0.78
    >>
    0.67
     >>>
    0.51
    )>>
    0.49
    >>↵
    0.47
    >>,
    0.46
    >>>
    0.45
    ?>>
    0.44
    >>(
    0.42
     >>↵↵
    0.42
    Act Density 0.020%

    No Known Activations