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

    Neuronpedia

    INDEX
    Explanations

    single words related to technological issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĥª
    -0.69
    ADRA
    -0.69
    »Ĵ
    -0.68
     tremend
    -0.66
     misdem
    -0.62
     Skydragon
    -0.61
     contrace
    -0.60
    ashtra
    -0.58
     Sabha
    -0.58
     ILCS
    -0.54
    POSITIVE LOGITS
    phant
    0.76
    hower
    0.72
    rency
    0.72
    ghan
    0.70
    uld
    0.70
    wald
    0.70
    merce
    0.69
    velt
    0.69
    rencies
    0.68
    rences
    0.68
    Act Density 2.547%

    No Known Activations