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

    Neuronpedia

    INDEX
    Explanations

    words related to systems, structures, and models

    oai_token-act-pair · gpt-3.5-turbo

    references to systems, structures, and ideologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cellaneous
    -0.63
     Fellow
    -0.62
     Returning
    -0.60
    PDATE
    -0.59
     Seym
    -0.58
    zens
    -0.57
    Americ
    -0.57
     Added
    -0.56
    gettable
    -0.56
    TPPStreamerBot
    -0.56
    POSITIVE LOGITS
     revolves
    1.69
     consists
    1.53
     involves
    1.44
     boils
    1.43
     relies
    1.43
     tends
    1.41
     sucks
    1.39
     differs
    1.38
     hinges
    1.33
     lacks
    1.33
    Act Density 0.393%

    No Known Activations