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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the letters "th"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igon
    -0.19
    igans
    -0.16
    antha
    -0.16
    ech
    -0.15
    paque
    -0.15
    erken
    -0.15
    orary
    -0.15
     Gran
    -0.14
    igel
    -0.14
    asz
    -0.14
    POSITIVE LOGITS
    rough
    0.21
    ematic
    0.21
     rough
    0.21
    rought
    0.20
     ere
    0.19
    ompson
    0.18
    ailand
    0.18
     Anniversary
    0.18
    yme
    0.18
    ematics
    0.18
    Act Density 0.034%

    No Known Activations