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

    Neuronpedia

    INDEX
    Explanations

    terms related to separation or categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Moss
    -0.15
     convenience
    -0.15
    管
    -0.14
     Skinner
    -0.14
    agi
    -0.14
     Geb
    -0.14
    Mos
    -0.14
    lys
    -0.14
     &
    -0.14
     Mol
    -0.14
    POSITIVE LOGITS
     оÑĤделÑĮ
    0.17
    akis
    0.16
     Separate
    0.16
    çį¨
    0.15
     separate
    0.14
     کاربر
    0.14
     окÑĢем
    0.14
     ä¸ĵ
    0.14
    alla
    0.14
     çevr
    0.14
    Act Density 0.196%

    No Known Activations