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

    Neuronpedia

    INDEX
    Explanations

    specific years or time periods

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    venge
    -0.71
    EStreamFrame
    -0.68
     lawy
    -0.64
    hed
    -0.61
    Edge
    -0.61
    hop
    -0.60
    vec
    -0.59
     verbs
    -0.58
    ube
    -0.58
     listener
    -0.57
    POSITIVE LOGITS
    -'
    1.06
     onwards
    0.98
    å¹
    0.94
     onward
    0.88
     BCE
    0.76
    ixties
    0.72
     census
    0.69
    çļ
    0.69
     Revision
    0.65
    âĢ²
    0.64
    Act Density 1.046%

    No Known Activations