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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "apply" within different contexts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    watching
    -0.70
    footed
    -0.66
    ument
    -0.64
    nia
    -0.64
    hoff
    -0.63
    birds
    -0.62
    aired
    -0.62
    owship
    -0.62
    acters
    -0.61
    bill
    -0.60
    POSITIVE LOGITS
     pressure
    0.95
     brakes
    0.72
     sunscreen
    0.71
    ogen
    0.68
     rigorous
    0.67
    arate
    0.65
     liber
    0.65
     lessons
    0.64
     lipstick
    0.64
     mathematical
    0.63
    Act Density 0.045%

    No Known Activations