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

    Neuronpedia

    INDEX
    Explanations

    references to collective identities or groups within a social context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Bauer
    -0.64
     Tale
    -0.63
    참고
    -0.63
    zt
    -0.61
    iop
    -0.57
    ar
    -0.56
     ваз
    -0.56
     dichos
    -0.56
     Vaz
    -0.56
     POS
    -0.55
    POSITIVE LOGITS
     everyone
    3.21
    everyone
    3.09
     Everyone
    2.96
     everybody
    2.95
    Everyone
    2.93
    everybody
    2.87
     Everybody
    2.87
    Everybody
    2.76
     EVERYONE
    2.68
    EVERY
    1.98
    Act Density 0.057%

    No Known Activations