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

    Neuronpedia

    INDEX
    Explanations

    texts related to organizations or laws

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations or concepts denoted by the abbreviation "OC"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     heights
    -0.72
    usha
    -0.68
     Bam
    -0.68
     fools
    -0.66
     Wick
    -0.65
     Harden
    -0.62
     fringe
    -0.62
     Reid
    -0.62
     awoken
    -0.62
     Shad
    -0.61
    POSITIVE LOGITS
    OC
    4.23
    oc
    1.85
     OC
    1.64
    OG
    1.52
    OT
    1.46
    OP
    1.45
    OGR
    1.36
    OA
    1.34
    OS
    1.33
    OD
    1.29
    Act Density 0.016%

    No Known Activations