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

    Neuronpedia

    INDEX
    Explanations

    pronouns and related references to individuals or groups in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ta
    -0.15
    IELD
    -0.15
    ánt
    -0.14
    avou
    -0.14
    urai
    -0.14
     launder
    -0.14
    ings
    -0.13
    ward
    -0.13
    год
    -0.13
    rib
    -0.13
    POSITIVE LOGITS
    haps
    0.16
    ceptor
    0.15
    eger
    0.15
    óng
    0.15
     PROGMEM
    0.14
    iazza
    0.14
    _queries
    0.14
     Tabs
    0.14
    aura
    0.13
    浩
    0.13
    Act Density 0.050%

    No Known Activations