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

    Neuronpedia

    INDEX
    Explanations

    phrases related to things being located or happening inside something

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "inside."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ellow
    -0.75
    eday
    -0.75
    oleon
    -0.74
    yah
    -0.72
    opter
    -0.68
    aler
    -0.68
    olk
    -0.67
    NF
    -0.65
    rought
    -0.65
    omen
    -0.64
    POSITIVE LOGITS
     parentheses
    0.75
     walls
    0.75
     cabinets
    0.74
     bedrooms
    0.71
     chambers
    0.69
     caves
    0.69
    SPONSORED
    0.68
     jars
    0.66
     containers
    0.65
     pockets
    0.63
    Act Density 0.051%

    No Known Activations