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

    Neuronpedia

    INDEX
    Explanations

    references to data types and structures used in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    name
    -0.17
    enthal
    -0.16
    side
    -0.15
     trÃŃ
    -0.15
    iar
    -0.15
    dess
    -0.15
    ãĥ¼ãĤ¸
    -0.15
    sing
    -0.15
    gregar
    -0.14
    time
    -0.14
    POSITIVE LOGITS
    osate
    0.17
    atsu
    0.16
    umin
    0.16
    gua
    0.16
    guns
    0.15
    alık
    0.14
    опиÑģ
    0.14
    езда
    0.14
    /terms
    0.14
     ÎĶια
    0.14
    Act Density 0.035%

    No Known Activations