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

    Neuronpedia

    INDEX
    Explanations

    phrases related to progression or advancement

    oai_token-act-pair · gpt-3.5-turbo

    sentences that indicate a conclusion or a shift in argument

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     malt
    -0.70
     himself
    -0.70
    imei
    -0.69
     flaw
    -0.68
     strictly
    -0.68
     deity
    -0.68
    yssey
    -0.68
     afterlife
    -0.67
     incur
    -0.65
     impartial
    -0.65
    POSITIVE LOGITS
     Suddenly
    1.30
     Already
    1.27
     Slowly
    1.26
     Increasing
    1.22
     Recently
    1.20
     Yesterday
    1.19
     Gone
    1.17
     Whereas
    1.15
     Earlier
    1.14
     Whether
    1.13
    Act Density 0.444%

    No Known Activations