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

    Neuronpedia

    INDEX
    Explanations

    references to large gatherings or crowds of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    crowds of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.73
     Numerade
    -0.45
    hyrchwyd
    -0.44
    SuppressLint
    -0.44
    upiter
    -0.44
    ANDUM
    -0.44
    quiti
    -0.42
    хьтан
    -0.42
    AccessorTable
    -0.41
    intios
    -0.41
    POSITIVE LOGITS
     crowd
    2.52
     crowds
    2.36
    crowd
    2.14
     Crowd
    1.93
    Crowd
    1.89
     CROW
    1.77
    crow
    1.55
     Crow
    1.47
    Crow
    1.47
     foule
    1.44
    Act Density 0.071%

    No Known Activations