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

    Neuronpedia

    INDEX
    Explanations

    press releases and information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    abama
    -0.76
     Reconstruction
    -0.70
    inho
    -0.68
     Haram
    -0.67
    alian
    -0.64
     Valhalla
    -0.63
     Scotia
    -0.62
     [|
    -0.62
    audi
    -0.61
     Trayvon
    -0.60
    POSITIVE LOGITS
    urized
    1.44
    ured
    1.04
    ures
    0.99
     conference
    0.92
    conference
    0.87
     corps
    0.86
     conferences
    0.86
    URE
    0.84
    ur
    0.83
    eval
    0.83
    Act Density 0.328%

    No Known Activations