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

    Neuronpedia

    INDEX
    Explanations

    terms related to measurements or evaluations in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jem
    -0.17
    пÑĢ
    -0.14
    ml
    -0.14
     Gaul
    -0.14
    ãĤ§
    -0.14
    ichte
    -0.14
    jis
    -0.14
    ules
    -0.14
    uto
    -0.14
    erset
    -0.14
    POSITIVE LOGITS
    asions
    0.18
    rish
    0.17
     Weston
    0.17
     ther
    0.16
    æģ¯
    0.16
    azzo
    0.16
    SG
    0.14
    год
    0.14
    eness
    0.14
     вÑĭдел
    0.14
    Act Density 0.006%

    No Known Activations