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

    Neuronpedia

    INDEX
    Explanations

    action-oriented commands and instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uien
    -0.15
    aben
    -0.14
    otor
    -0.14
     character
    -0.14
     mennes
    -0.13
    ”ãĢĤ
    -0.13
    ennon
    -0.13
     "$
    -0.13
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    -0.13
    ekil
    -0.13
    POSITIVE LOGITS
    978
    0.17
    alian
    0.17
     AndAlso
    0.15
    882
    0.15
    ccd
    0.14
     âĢº
    0.14
    ži
    0.14
    ATOM
    0.13
    .za
    0.13
    982
    0.13
    Act Density 1.554%

    No Known Activations