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

    Neuronpedia

    INDEX
    Explanations

    compound words and terms related to duality or pairs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soever
    -0.17
    prit
    -0.17
    isci
    -0.16
    imson
    -0.15
    imenti
    -0.15
    ampler
    -0.15
    iku
    -0.14
    alion
    -0.14
     vůbec
    -0.14
    кÑĸн
    -0.14
    POSITIVE LOGITS
    /single
    0.33
    -double
    0.21
     double
    0.21
    ,double
    0.21
    -single
    0.21
    ouble
    0.20
     Double
    0.20
    tons
    0.19
    (single
    0.19
    ended
    0.17
    Act Density 0.089%

    No Known Activations