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

    Neuronpedia

    INDEX
    Explanations

    combinations of the words "black" and "and" that are adjacent to each other

    oai_token-act-pair · gpt-3.5-turbo

    patterns involving the phrase "black and white."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udence
    -0.75
     Administ
    -0.75
    issance
    -0.75
    enza
    -0.73
    Cons
    -0.73
    ctors
    -0.72
    Series
    -0.72
     Ratings
    -0.72
    VERTISEMENT
    -0.71
    utsu
    -0.71
    POSITIVE LOGITS
     white
    1.15
     yellow
    1.12
    white
    1.10
     grey
    1.08
     gray
    1.07
     brown
    1.07
     orange
    1.05
     blue
    1.04
     striped
    1.01
     purple
    1.00
    Act Density 0.073%

    No Known Activations