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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decisions, actions, or recommendations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    VICE
    -0.69
     CLSID
    -0.62
    9999
    -0.57
     understatement
    -0.53
    akia
    -0.51
     Xin
    -0.50
     Kahn
    -0.50
     VIDEOS
    -0.50
    ATA
    -0.50
     healing
    -0.49
    POSITIVE LOGITS
    raised
    0.99
    grading
    0.91
    dating
    0.90
    stairs
    0.90
    dates
    0.90
    ended
    0.90
    rated
    0.89
    swing
    0.89
    graded
    0.84
    rights
    0.84
    Act Density 0.037%

    No Known Activations