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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or states of being

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     dumps
    -0.67
     sleeps
    -0.60
     AMA
    -0.60
     shoots
    -0.60
     bedrooms
    -0.58
     wakes
    -0.58
     watches
    -0.57
     Atmosp
    -0.56
     plots
    -0.56
     Sask
    -0.56
    POSITIVE LOGITS
    ŃĶ
    0.69
    oldown
    0.65
     fraught
    0.65
    1027
    0.64
    SourceFile
    0.64
    iHUD
    0.62
     hampered
    0.62
     justified
    0.61
    factor
    0.61
    Factor
    0.60
    Act Density 0.810%

    No Known Activations