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

    Neuronpedia

    INDEX
    Explanations

    phrases related to problem-solving and decision-making

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to problem-solving and figuring things out

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.78
    isSpecialOrderable
    -0.73
    BuyableInstoreAndOnline
    -0.70
    ONG
    -0.68
     Aware
    -0.68
    IUM
    -0.64
    oscope
    -0.63
    interstitial
    -0.61
    ORS
    -0.61
    orescent
    -0.61
    POSITIVE LOGITS
     how
    1.45
     why
    1.35
     ways
    1.25
     what
    1.20
     exactly
    1.14
     whats
    1.13
     WHY
    1.13
     HOW
    1.09
     whether
    1.08
     whence
    1.05
    Act Density 0.047%

    No Known Activations