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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the substring "th" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akens
    -0.16
    edback
    -0.16
    zer
    -0.16
    illez
    -0.16
    .githubusercontent
    -0.16
    ech
    -0.16
    paque
    -0.16
    ìĽĶ
    -0.15
    ease
    -0.15
    liž
    -0.14
    POSITIVE LOGITS
     th
    0.17
    zas
    0.17
    INK
    0.17
    ousands
    0.17
     ere
    0.17
    inks
    0.17
    sst
    0.16
    omas
    0.16
    elper
    0.16
    ttp
    0.16
    Act Density 0.026%

    No Known Activations