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

    Neuronpedia

    INDEX
    Explanations

    terms related to units of measurement and categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inals
    -0.16
    ãģ¯ãģļ
    -0.15
    interopRequire
    -0.15
    ạn
    -0.14
    sst
    -0.14
    ITTE
    -0.14
    ernet
    -0.14
     اÙĦتÙģ
    -0.14
    anel
    -0.14
    åĭ
    -0.14
    POSITIVE LOGITS
     Antar
    0.18
    สาร
    0.15
    ÑĥÑĤ
    0.14
    кÑĥлÑĮ
    0.14
     pulp
    0.13
    ptron
    0.13
    ÙĦت
    0.13
     ÑĢазв
    0.13
    YPES
    0.13
    ROADCAST
    0.13
    Act Density 0.082%

    No Known Activations