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

    Neuronpedia

    INDEX
    Explanations

    documentaries and journalism-related content

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    asus
    -0.70
    oux
    -0.67
     subsistence
    -0.67
    uez
    -0.63
     jurisd
    -0.60
    IBLE
    -0.59
     wheelchair
    -0.59
    blind
    -0.59
    ultimate
    -0.59
    shield
    -0.58
    POSITIVE LOGITS
    uggest
    1.43
    hops
    1.02
    mith
    1.02
    chool
    0.99
    ynthesis
    0.91
     depicting
    0.90
    ilver
    0.89
    CRIP
    0.89
    hare
    0.89
    linger
    0.88
    Act Density 0.211%

    No Known Activations