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

    Neuronpedia

    INDEX
    Explanations

    descriptions of physical actions and sequences of events happening in a narrative

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    rain
    -1.02
    ãĥķãĤ¡
    -0.96
    Times
    -0.96
    NULL
    -0.95
    gradation
    -0.94
    emo
    -0.92
    ifferent
    -0.91
    ict
    -0.91
    gress
    -0.90
    uci
    -0.90
    POSITIVE LOGITS
     consequently
    1.80
     therefore
    1.66
     hence
    1.59
     thus
    1.58
     then
    1.57
     secondly
    1.56
     thereby
    1.50
     subsequently
    1.33
     hopefully
    1.32
     possibly
    1.31
    Act Density 1.655%

    No Known Activations