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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, such as names of people and places

    oai_token-act-pair · gpt-3.5-turbo

    numerical representations or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thereof
    -0.63
     respectively
    -0.62
     thereto
    -0.59
    %).
    -0.53
     therein
    -0.50
    )."
    -0.49
    venge
    -0.48
    ?).
    -0.48
     risking
    -0.47
     });
    -0.47
    POSITIVE LOGITS
     âĵĺ
    0.70
    ':
    0.70
     Edit
    0.69
     Profile
    0.68
    !:
    0.62
    udos
    0.57
     meanwhile
    0.57
     UPDATE
    0.56
     Spiel
    0.54
     Emails
    0.54
    Act Density 1.125%

    No Known Activations