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

    Neuronpedia

    INDEX
    Explanations

    references to storytelling and lyrics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    inence
    -0.78
    orem
    -0.78
    ignt
    -0.75
    achev
    -0.73
    owered
    -0.72
    bledon
    -0.70
    hammad
    -0.70
    agles
    -0.69
    aurus
    -0.69
    ategory
    -0.68
    POSITIVE LOGITS
    telling
    1.36
     arcs
    1.01
    te
    0.98
     arc
    0.97
    tell
    0.89
    book
    0.86
     synopsis
    0.86
    line
    0.84
    tale
    0.84
     reprinted
    0.84
    Act Density 0.677%

    No Known Activations