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

    Neuronpedia

    INDEX
    Explanations

    email addresses and headers

    oai_token-act-pair · gpt-3.5-turbo

    references to email communications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avorite
    -0.87
     tremend
    -0.80
    etheless
    -0.69
     momentarily
    -0.66
    inarily
    -0.66
     recalled
    -0.65
    acity
    -0.65
     simultane
    -0.64
    ixel
    -0.63
     explan
    -0.63
    POSITIVE LOGITS
     Unknown
    0.92
     Cosponsors
    0.90
     Various
    0.88
     Anonymous
    0.83
     ©
    0.83
     Karl
    0.75
     Logged
    0.74
     Misc
    0.74
     HUM
    0.73
     é
    0.73
    Act Density 0.071%

    No Known Activations