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

    Neuronpedia

    INDEX
    Explanations

    important information or details in sentences

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Soup
    -0.62
     Codes
    -0.59
     goose
    -0.58
     ect
    -0.57
     combinations
    -0.55
    Submit
    -0.54
     homemade
    -0.54
    Joined
    -0.54
    codes
    -0.53
     spontaneous
    -0.53
    POSITIVE LOGITS
     note
    1.30
     realize
    1.19
     realise
    1.16
     remember
    1.07
     beware
    1.05
     acknowledge
    1.03
     notice
    1.02
    remember
    0.99
     noting
    0.98
     consider
    0.98
    Act Density 0.216%

    No Known Activations