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

    Neuronpedia

    INDEX
    Explanations

    technical or scientific terms and concepts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ching
    -0.68
     franc
    -0.65
    lder
    -0.64
    ++++++++
    -0.62
     frag
    -0.61
    ched
    -0.60
     Bolivia
    -0.59
     Honduras
    -0.59
     quo
    -0.59
    prints
    -0.59
    POSITIVE LOGITS
    etheus
    1.03
    orph
    1.01
    essage
    0.93
    ammu
    0.93
    ont
    0.92
    yss
    0.92
    ingo
    0.91
    osal
    0.87
    sg
    0.86
    pter
    0.86
    Act Density 0.018%

    No Known Activations