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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal and social issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    bats
    -0.69
    course
    -0.69
    furt
    -0.66
    noticed
    -0.65
    specified
    -0.62
     Rapids
    -0.61
    icipated
    -0.59
    alde
    -0.59
    river
    -0.58
    times
    -0.58
    POSITIVE LOGITS
     specialize
    0.90
     represent
    0.85
     derive
    0.85
     embody
    0.85
     solve
    0.82
     diagnose
    0.81
     recreate
    0.81
     perform
    0.80
     originate
    0.79
     equate
    0.79
    Act Density 0.025%

    No Known Activations