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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating physical location or relation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "beneath" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yah
    -0.87
    atic
    -0.75
    ordan
    -0.74
    eln
    -0.73
    DN
    -0.71
     Preferred
    -0.69
    zai
    -0.69
    ctions
    -0.68
    cker
    -0.66
    iji
    -0.66
    POSITIVE LOGITS
    neath
    1.18
    eatures
    1.02
     layers
    0.92
    pins
    0.88
     beneath
    0.87
    sea
    0.85
    ĸļ
    0.85
     underneath
    0.80
     lip
    0.78
    ĨĴ
    0.73
    Act Density 0.027%

    No Known Activations