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

    Neuronpedia

    INDEX
    Explanations

    arguments and philosophical statements

    oai_token-act-pair · gpt-3.5-turbo

    arguments and concepts related to philosophy and morality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adelphia
    -0.84
    Street
    -0.82
    elight
    -0.79
     VIP
    -0.79
     Shots
    -0.79
    leased
    -0.76
     Celeb
    -0.75
    Town
    -0.75
     Chattanooga
    -0.73
    Cele
    -0.73
    POSITIVE LOGITS
     presupp
    1.73
     epist
    1.56
     empir
    1.53
     theorem
    1.49
     logically
    1.48
     fallacy
    1.40
     empirical
    1.39
     ont
    1.35
     metaphysical
    1.34
     philosophers
    1.30
    Act Density 0.491%

    No Known Activations