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

    Neuronpedia

    INDEX
    Explanations

    language that indicates communication and expression of feelings or thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orsk
    -0.16
    شتÙĩ
    -0.15
    759
    -0.15
    кин
    -0.14
    ãĥĪãĥª
    -0.14
     Silva
    -0.14
    ÑĥÑĩа
    -0.13
     Blick
    -0.13
    iller
    -0.13
     Ñģобой
    -0.13
    POSITIVE LOGITS
    flammatory
    0.15
     PyErr
    0.14
    fork
    0.14
    æĻ´
    0.14
    ubble
    0.14
    assandra
    0.14
    ëĭ´
    0.14
    ffen
    0.14
     Lyons
    0.14
    Äįer
    0.13
    Act Density 0.570%

    No Known Activations