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

    Neuronpedia

    INDEX
    Explanations

    terms related to a broad or encompassing category or concept

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "umbrella" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nesota
    -0.82
    anooga
    -0.82
    avery
    -0.81
    awar
    -0.77
    achy
    -0.76
    onew
    -0.73
    eph
    -0.71
    esters
    -0.70
    ogan
    -0.70
    cision
    -0.69
    POSITIVE LOGITS
     umbrella
    1.09
     umb
    0.88
    vine
    0.75
     wip
    0.73
     poles
    0.71
     cord
    0.70
     blanket
    0.69
    tip
    0.68
     pole
    0.65
     sill
    0.64
    Act Density 0.014%

    No Known Activations