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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases indicating time or completion

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.70
    wx
    -0.68
    eer
    -0.65
    achy
    -0.61
    ened
    -0.61
    orthy
    -0.60
    anan
    -0.59
    ï¸ı
    -0.59
    ensitive
    -0.59
    -+
    -0.58
    POSITIVE LOGITS
     rope
    0.95
    course
    0.77
    veyard
    0.77
     nowhere
    0.75
     leash
    0.73
     ropes
    0.73
     runway
    0.72
     tether
    0.71
     spectrum
    0.70
    hours
    0.67
    Act Density 0.075%

    No Known Activations