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

    Neuronpedia

    INDEX
    Explanations

    references to communication interactions and timelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _scaling
    -0.15
    ç»Ń
    -0.14
    adoo
    -0.14
     trunc
    -0.14
    airo
    -0.13
    _reserve
    -0.13
    isodes
    -0.13
    nten
    -0.13
    ETCH
    -0.13
    ahoo
    -0.12
    POSITIVE LOGITS
    ICH
    0.18
    ÏĢη
    0.17
    _mk
    0.15
    PIO
    0.14
    IMER
    0.14
    alli
    0.13
    amax
    0.13
    -flash
    0.13
    ichen
    0.13
     Brom
    0.13
    Act Density 0.007%

    No Known Activations