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

    Neuronpedia

    INDEX
    Explanations

    solutions and proposals mentioned in technical contexts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     ¯
    -0.86
     Frie
    -0.71
    issance
    -0.69
    igion
    -0.65
     Dragonbound
    -0.63
    feeding
    -0.62
     Sandwich
    -0.61
     Ends
    -0.60
     Median
    -0.60
     Advertisement
    -0.59
    POSITIVE LOGITS
     vying
    1.18
     simultaneously
    0.97
     grouped
    0.89
     interconnected
    0.89
     arisen
    0.87
     concurrently
    0.83
     conver
    0.83
     implicated
    0.82
     intertwined
    0.81
     clustered
    0.81
    Act Density 0.283%

    No Known Activations