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

    Neuronpedia

    INDEX
    Explanations

    verbs related to the act of taking

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    enegger
    -0.71
    lich
    -0.67
    ateg
    -0.63
    atum
    -0.62
    ibel
    -0.62
    bach
    -0.61
     ---------
    -0.59
     coerc
    -0.59
     athlet
    -0.58
    illing
    -0.57
    POSITIVE LOGITS
     advantage
    1.08
     precedence
    1.06
     refuge
    1.00
     care
    0.93
     hold
    0.90
    aways
    0.88
     aback
    0.86
     control
    0.84
     root
    0.82
     notice
    0.82
    Act Density 0.119%

    No Known Activations