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

    Neuronpedia

    INDEX
    Explanations

    linguistic constructs involving prepositions and their relationships

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

    "on" followed by "the", "a", or "an"

    np_acts-logits-general · gemini-2.0-flash

    dependent on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.73
     Shakspeare
    -0.72
     Shaksp
    -0.70
     Hopf
    -0.69
     Cæsar
    -0.68
     Anſ
    -0.63
     ajuns
    -0.63
     Mahomet
    -0.62
     alfo
    -0.62
     Mahabhar
    -0.61
    POSITIVE LOGITS
     the
    1.65
     a
    1.11
     an
    1.06
     those
    0.97
     what
    0.95
     their
    0.93
    "])
    0.91
     both
    0.88
     our
    0.87
    "):
    0.87
    Act Density 1.979%

    No Known Activations