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

    Neuronpedia

    INDEX
    Explanations

    compliments or positive remarks from informal discussions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.79
    çķ
    -0.75
    ç«
    -0.75
    ãĥĺãĥ©
    -0.73
    à¨
    -0.72
    à©
    -0.68
    perature
    -0.68
    ajor
    -0.68
    conservancy
    -0.67
    artney
    -0.66
    POSITIVE LOGITS
     huh
    1.01
    ly
    0.99
     irony
    0.93
     kidding
    0.90
     coincidence
    0.87
     Tracks
    0.82
     Enough
    0.82
     Thoughts
    0.81
    bye
    0.80
     Facts
    0.79
    Act Density 0.122%

    No Known Activations