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

    Neuronpedia

    INDEX
    Explanations

    references to scientific classifications and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cntl
    -0.16
    onnement
    -0.16
    abra
    -0.15
    umont
    -0.15
    ustainability
    -0.14
     ((__
    -0.14
    andel
    -0.14
    reeze
    -0.14
    ymm
    -0.14
    _DISPATCH
    -0.14
    POSITIVE LOGITS
     factor
    0.15
    Factor
    0.15
    αν
    0.15
     Factor
    0.15
     Rever
    0.14
    rad
    0.14
    adero
    0.14
     rever
    0.14
     ITS
    0.14
    ower
    0.13
    Act Density 0.003%

    No Known Activations