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

    Neuronpedia

    INDEX
    Explanations

    words related to memory and cognition

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to memory and individual identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çīĪ
    -0.71
    BuyableInstoreAndOnline
    -0.70
    Mich
    -0.69
    Tour
    -0.68
     Toledo
    -0.67
    Yan
    -0.66
    Mi
    -0.65
    oute
    -0.64
    Dispatch
    -0.64
    Works
    -0.64
    POSITIVE LOGITS
     inherently
    1.05
     therefore
    0.87
     intrinsically
    0.87
     everywhere
    0.85
     pervasive
    0.85
     primarily
    0.81
     concentrated
    0.80
     NEVER
    0.79
     fundamentally
    0.78
     indeed
    0.78
    Act Density 0.520%

    No Known Activations