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

    Neuronpedia

    INDEX
    Explanations

    mentions of the end of events or time periods

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     darling
    -0.77
     Cosponsors
    -0.76
    anan
    -0.75
    OY
    -0.71
    alogy
    -0.68
    webkit
    -0.67
     faire
    -0.66
     additionally
    -0.66
    RED
    -0.65
    Reviewer
    -0.64
    POSITIVE LOGITS
     rope
    0.90
     hostilities
    0.83
     course
    0.82
    sight
    0.80
     nowhere
    0.79
    spection
    0.78
    course
    0.76
    struct
    0.75
    agall
    0.74
    notes
    0.72
    Act Density 11.070%

    No Known Activations