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

    Neuronpedia

    INDEX
    Explanations

    words related to evaluating options, considerations, and making decisions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ahime
    -0.83
    employment
    -0.80
    claimed
    -0.79
    etheless
    -0.79
    esan
    -0.79
    zynski
    -0.76
    ellen
    -0.75
    interrupted
    -0.74
     Leilan
    -0.74
    gradation
    -0.74
    POSITIVE LOGITS
     weigh
    1.30
     weights
    1.06
     weighing
    1.04
    ighed
    0.98
     weighed
    0.92
    iless
    0.87
     weighs
    0.85
     burdens
    0.81
     heaviest
    0.81
     pedals
    0.80
    Act Density 6.700%

    No Known Activations