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

    Neuronpedia

    INDEX
    Explanations

    concepts related to strategy and evaluation in decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    duk
    -0.15
    ledik
    -0.14
    zb
    -0.14
    dq
    -0.14
     SLOT
    -0.14
    kre
    -0.14
    CTL
    -0.13
     indoor
    -0.13
     zeros
    -0.13
    vr
    -0.13
    POSITIVE LOGITS
     íĮ¨
    0.16
    etto
    0.15
    acon
    0.14
     continuation
    0.14
     oppon
    0.14
    Ã
    0.14
     Clock
    0.14
    人çī©
    0.13
    oplay
    0.13
     ÑĢазви
    0.13
    Act Density 0.002%

    No Known Activations