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

    Neuronpedia

    INDEX
    Explanations

    comparisons in performance or rankings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     notwithstanding
    -0.63
     ********************************
    -0.54
     WATCHED
    -0.54
     reperto
    -0.54
    meet
    -0.53
    ¯¯¯¯¯¯¯¯
    -0.52
     ASAP
    -0.52
    word
    -0.52
     although
    -0.51
    Dial
    -0.51
    POSITIVE LOGITS
     others
    0.95
     ours
    0.92
     elsewhere
    0.87
     theirs
    0.85
     actual
    0.83
     other
    0.82
     yours
    0.78
     hers
    0.76
     rest
    0.71
    actual
    0.70
    Act Density 2.711%

    No Known Activations