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

    Neuronpedia

    INDEX
    Explanations

    references to specific names and entities across different contexts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    uality
    -1.09
    nces
    -1.05
    igslist
    -1.02
    ahead
    -0.97
    ainer
    -0.95
    Downloadha
    -0.94
     validity
    -0.92
    URES
    -0.90
     Leone
    -0.88
    Import
    -0.88
    POSITIVE LOGITS
    mers
    1.93
    pton
    1.62
    strings
    1.61
    wich
    1.58
    ster
    1.55
    elin
    1.54
    ilton
    1.53
    monds
    1.50
    ming
    1.49
    mer
    1.46
    Act Density 1.288%

    No Known Activations