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

    Neuronpedia

    INDEX
    Explanations

    the presence of the word "the" and its contextual associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enou
    -0.16
    ochen
    -0.15
    ucz
    -0.15
    .od
    -0.14
    CRET
    -0.14
    ĩ´
    -0.14
     Brooke
    -0.14
     skoro
    -0.14
    adium
    -0.14
    átek
    -0.14
    POSITIVE LOGITS
     Pie
    0.18
    ales
    0.15
    outu
    0.15
     pie
    0.15
     Huff
    0.15
    avel
    0.14
    hoot
    0.14
    die
    0.14
     Trou
    0.14
    uste
    0.14
    Act Density 0.140%

    No Known Activations