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

    Neuronpedia

    INDEX
    Explanations

    terms related to various professions or fields of expertise

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various fields of professional expertise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    selves
    -0.88
     Countries
    -0.81
     Balls
    -0.80
     Characters
    -0.80
     Ones
    -0.80
     Pieces
    -0.78
     Result
    -0.74
     Soldiers
    -0.72
     Winners
    -0.72
     Piece
    -0.72
    POSITIVE LOGITS
     sciences
    1.08
     anthropology
    1.03
     strategist
    1.00
     consulting
    0.97
     sociology
    0.97
     affairs
    0.96
     advisory
    0.96
     psychologist
    0.94
     analytics
    0.94
     ecology
    0.93
    Act Density 0.289%

    No Known Activations