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

    Neuronpedia

    INDEX
    Explanations

    expressions that denote conditions, possibilities, or summarizations of complex relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    argon
    -0.16
     gn
    -0.16
    ØŃÙĦ
    -0.16
    [args
    -0.15
    linger
    -0.15
    iddi
    -0.14
    aight
    -0.14
     arg
    -0.14
    (ARG
    -0.14
    ascus
    -0.14
    POSITIVE LOGITS
    quine
    0.16
     LRV
    0.15
     Rip
    0.15
     Pratt
    0.15
     Canary
    0.15
    ombs
    0.15
     complimentary
    0.14
    cilik
    0.14
    -Sah
    0.14
     agency
    0.14
    Act Density 0.009%

    No Known Activations