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

    Neuronpedia

    INDEX
    Explanations

    quantifiers indicating large or notable quantities of people or things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arÃŃa
    -0.08
    utable
    -0.07
    usher
    -0.07
    æĭĽ
    -0.07
    eson
    -0.07
    ught
    -0.07
    ød
    -0.07
    оÑĤÑĮ
    -0.07
     Aires
    -0.07
    idunt
    -0.07
    POSITIVE LOGITS
     are
    0.14
     them
    0.13
     others
    0.11
     have
    0.10
     ones
    0.10
    them
    0.09
     will
    0.09
     who
    0.08
     cannot
    0.08
     Others
    0.08
    Act Density 0.059%

    No Known Activations