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

    Neuronpedia

    INDEX
    Explanations

    references to training programs or competitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apist
    -0.15
    @a
    -0.15
     Stable
    -0.14
    nob
    -0.14
     Assassin
    -0.14
    RIX
    -0.14
     disclaimer
    -0.13
     GENERIC
    -0.13
    imple
    -0.13
     stable
    -0.13
    POSITIVE LOGITS
     æ¿
    0.17
    uml
    0.16
    isode
    0.15
     Prelude
    0.15
    ļĮ
    0.15
    lbrace
    0.15
    isodes
    0.15
    asca
    0.14
    eds
    0.14
    aga
    0.14
    Act Density 0.123%

    No Known Activations