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

    Neuronpedia

    INDEX
    Explanations

    instances of monetary values expressed in numbers

    oai_token-act-pair · gpt-3.5-turbo

    specific letters or characters appearing in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Moff
    -0.60
     Gamble
    -0.53
     Osw
    -0.52
     Gadget
    -0.50
     AE
    -0.50
     HIP
    -0.46
     commenting
    -0.45
    advertising
    -0.43
     EVs
    -0.43
     BMC
    -0.42
    POSITIVE LOGITS
    arant
    0.68
    alin
    0.67
    otom
    0.63
    anche
    0.61
    iren
    0.61
    odox
    0.61
    omas
    0.60
    ioned
    0.59
    yth
    0.59
    roid
    0.58
    Act Density 1.705%

    No Known Activations