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

    Neuronpedia

    INDEX
    Explanations

    expressions referring to technical processes or commands

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to missing elements or components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     seiz
    -0.77
    afety
    -0.68
    comfort
    -0.66
     conduc
    -0.64
    ARS
    -0.62
     fortun
    -0.62
    ways
    -0.62
    gently
    -0.60
     straps
    -0.60
    sight
    -0.59
    POSITIVE LOGITS
    ļéĨĴ
    0.80
    catentry
    0.72
    aeper
    0.69
     Ibid
    0.67
    BuyableInstoreAndOnline
    0.67
    EStream
    0.63
    otom
    0.63
    ñ
    0.61
    STDOUT
    0.61
     Mitt
    0.60
    Act Density 0.408%

    No Known Activations