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

    Neuronpedia

    INDEX
    Explanations

    specific technical features or functionalities in software or devices

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    hiba
    -0.82
    sis
    -0.80
    esta
    -0.78
    externalActionCode
    -0.73
    alg
    -0.72
     millenn
    -0.71
    kos
    -0.71
    arger
    -0.68
    abama
    -0.67
    vernment
    -0.66
    POSITIVE LOGITS
     prominently
    1.00
    hered
    0.92
    ttes
    0.85
    ivity
    0.82
    ious
    0.81
    ioned
    0.80
    witz
    0.79
    aceous
    0.78
    iveness
    0.77
     features
    0.72
    Act Density 0.799%

    No Known Activations