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

    Neuronpedia

    INDEX
    Explanations

    words related to surnames or last names

    oai_token-act-pair · gpt-3.5-turbo

    the letter "b" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lauder
    -0.73
    DEM
    -0.65
    æ©Ł
    -0.61
    eers
    -0.61
     nomine
    -0.61
     Gutenberg
    -0.59
    Magikarp
    -0.58
     Porsche
    -0.58
    bilt
    -0.58
    ãĥ´ãĤ¡
    -0.57
    POSITIVE LOGITS
    rief
    1.36
    odies
    1.22
    ruary
    1.15
    attery
    1.11
    reath
    1.08
    anned
    1.07
    amboo
    1.06
    rows
    1.05
    ibli
    1.05
    ureau
    1.04
    Act Density 0.044%

    No Known Activations