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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical or physical concepts, particularly related to "forces" or "factors."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote quantities or factors related to physical forces or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    days
    -0.75
    ipeg
    -0.66
    ãģ®å®
    -0.64
    iversary
    -0.60
     Topic
    -0.60
     Buckingham
    -0.60
     Gazette
    -0.59
     Idea
    -0.59
     Hemp
    -0.59
    576
    -0.58
    POSITIVE LOGITS
     causation
    0.78
    upper
    0.73
    ocus
    0.72
    udic
    0.66
    ãĥ¼ãĥĨ
    0.66
     mater
    0.65
     exerted
    0.65
    effic
    0.65
    ativity
    0.64
    omaly
    0.63
    Act Density 0.719%

    No Known Activations