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

    Neuronpedia

    INDEX
    Explanations

    phrases related to step-by-step instructions or processes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    luaj
    -0.80
     scraps
    -0.68
    coni
    -0.67
    76561
    -0.67
    United
    -0.66
     Predator
    -0.63
    zsche
    -0.62
    ITED
    -0.61
    ãĥĩãĤ£
    -0.60
     Pengu
    -0.60
    POSITIVE LOGITS
     steps
    0.81
    udic
    0.76
     step
    0.75
     Steps
    0.75
    steps
    0.74
     verification
    0.69
     paddle
    0.68
     bypass
    0.68
     stride
    0.68
    verning
    0.68
    Act Density 0.101%

    No Known Activations