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

    Neuronpedia

    INDEX
    Explanations

    questions ending with a question mark

    oai_token-act-pair · gpt-3.5-turbo

    questions aimed at engaging readers or prompting interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scapego
    -0.73
    alty
    -0.72
     reven
    -0.71
    aling
    -0.71
    als
    -0.70
    aper
    -0.69
    iculture
    -0.69
    riet
    -0.68
     manif
    -0.67
    al
    -0.66
    POSITIVE LOGITS
     Nope
    0.99
     Check
    0.92
     Wouldn
    0.87
     Yep
    0.85
     Maybe
    0.85
     Probably
    0.83
     Answer
    0.82
     Think
    0.82
     Well
    0.82
     Sure
    0.81
    Act Density 0.096%

    No Known Activations