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

    Neuronpedia

    INDEX
    Explanations

    numerical values and mathematical operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Borne
    -0.56
    onus
    -0.53
    <![
    -0.51
    nial
    -0.51
    arna
    -0.50
     associate
    -0.49
    haden
    -0.49
     stretcher
    -0.48
    Ferguson
    -0.48
    Anastasia
    -0.47
    POSITIVE LOGITS
    7
    1.58
     seventh
    1.38
     seven
    1.36
     Seven
    1.33
     Seventh
    1.28
     SEVEN
    1.22
    seven
    1.19
     tujuh
    1.17
    seventh
    1.16
    七
    1.16
    Act Density 0.882%

    No Known Activations