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

    Neuronpedia

    INDEX
    Explanations

    information related to references, citations, and further reading in text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    hement
    -0.69
     layoffs
    -0.66
     neighb
    -0.62
    ufact
    -0.62
     hous
    -0.61
    rency
    -0.60
     ende
    -0.59
    kefeller
    -0.59
     neigh
    -0.58
    staking
    -0.58
    POSITIVE LOGITS
    References
    0.99
    pmwiki
    0.87
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.81
    Trivia
    0.80
    âĨij
    0.79
    Sources
    0.78
    Notes
    0.76
    notations
    0.76
    Characters
    0.71
    itars
    0.69
    Act Density 16.103%

    No Known Activations