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

    Neuronpedia

    INDEX
    Explanations

    textual references to scientific results and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wan
    -0.16
     flor
    -0.14
     sense
    -0.14
    âĢº
    -0.14
    ynam
    -0.14
     U
    -0.14
     Sag
    -0.14
     Pri
    -0.14
     vague
    -0.13
    rets
    -0.13
    POSITIVE LOGITS
    426
    0.16
    toa
    0.15
    ookies
    0.14
    ASA
    0.14
    /Instruction
    0.14
    ephy
    0.14
    ftime
    0.14
    иÑģÑĮ
    0.14
    -Allow
    0.14
    ***↵↵
    0.14
    Act Density 0.049%

    No Known Activations