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

    Neuronpedia

    INDEX
    Explanations

    questions or topics of discussion

    oai_token-act-pair · gpt-3.5-turbo

    concepts, questions, and objects of inquiry related to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    racuse
    -0.71
     Courier
    -0.65
     Crush
    -0.59
     Temper
    -0.59
    du
    -0.59
    Dub
    -0.58
     Blaster
    -0.58
    rick
    -0.58
    fac
    -0.57
     RTX
    -0.57
    POSITIVE LOGITS
    hips
    1.05
     belong
    0.93
    hip
    0.87
    folk
    0.83
    hops
    0.81
    mith
    0.80
     are
    0.79
    ettings
    0.77
     constitute
    0.77
     belonged
    0.74
    Act Density 0.266%

    No Known Activations