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

    Neuronpedia

    INDEX
    Explanations

    information related to news and articles

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    hement
    -0.59
    abouts
    -0.45
     manoeuv
    -0.45
    allas
    -0.42
    abwe
    -0.42
     estranged
    -0.42
    furt
    -0.41
    atri
    -0.41
    atory
    -0.40
     repatri
    -0.40
    POSITIVE LOGITS
     Norn
    0.55
     Spice
    0.54
     :)
    0.53
    âĻ¥
    0.52
    Anyway
    0.51
    âĺħ
    0.49
     ;)
    0.49
    Seriously
    0.49
    YES
    0.49
    Congratulations
    0.47
    Act Density 8.930%

    No Known Activations