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

    Neuronpedia

    INDEX
    Explanations

    slashes ('/') followed by numbers

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     notices
    -0.78
     glide
    -0.78
     demol
    -0.77
     creep
    -0.77
     accus
    -0.77
     wrench
    -0.75
     sweeping
    -0.73
     stalking
    -0.73
     plants
    -0.73
     elim
    -0.73
    POSITIVE LOGITS
    Flickr
    1.33
    etc
    1.28
    Getty
    1.27
    CN
    1.13
    Gall
    1.13
    Kin
    1.12
    ãĤ¨ãĥ«
    1.10
    whatever
    1.10
    CIA
    1.08
    CI
    1.08
    Act Density 0.071%

    No Known Activations