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

    Neuronpedia

    INDEX
    Explanations

    terms related to diversity and individual identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onders
    -0.15
    bd
    -0.14
     misuse
    -0.14
    ylon
    -0.14
    ud
    -0.14
    èĦ±
    -0.14
    arez
    -0.14
    Ñİ
    -0.13
     illeg
    -0.13
     bes
    -0.13
    POSITIVE LOGITS
     communities
    0.16
    ţi
    0.15
    thouse
    0.15
    ANJI
    0.15
    Slinky
    0.15
     Communities
    0.15
    SelectionMode
    0.14
    ør
    0.14
    877
    0.14
    asca
    0.14
    Act Density 0.006%

    No Known Activations