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

    Neuronpedia

    INDEX
    Explanations

    mentions of political figures, particularly U.S. presidents and their actions

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

    Follows the title "President"

    np_acts-logits-general · gemini-2.0-flash

    president followed by name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Salter
    -0.61
     للمعارف
    -0.60
    Vectors
    -0.57
     Vectors
    -0.55
    Vector
    -0.55
     vectors
    -0.54
     Vector
    -0.54
     VECTOR
    -0.53
    wickshire
    -0.52
    VECTOR
    -0.52
    POSITIVE LOGITS
     President
    1.68
     Obama
    1.63
    President
    1.51
     Trump
    1.45
     Barack
    1.42
     president
    1.39
    Obama
    1.38
     Bush
    1.27
    Trump
    1.26
     PRESIDENT
    1.23
    Act Density 0.364%

    No Known Activations