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

    Neuronpedia

    INDEX
    Explanations

    names with the pattern "ker" followed by a number ranging from 5 to 10

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cind
    -0.68
    ashtra
    -0.68
    ental
    -0.66
    Reviewer
    -0.66
    icist
    -0.64
    ollah
    -0.63
     constitu
    -0.63
     Palestin
    -0.60
    ella
    -0.58
    querque
    -0.58
    POSITIVE LOGITS
    chief
    1.01
    haw
    0.92
    luster
    0.91
    wagen
    0.90
    ker
    0.89
    kie
    0.84
    crew
    0.80
    rieg
    0.79
    lar
    0.78
    rish
    0.76
    Act Density 0.043%

    No Known Activations