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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kont
    -0.15
    kiem
    -0.15
    zap
    -0.15
    ivial
    -0.15
    pte
    -0.14
    anga
    -0.14
    anto
    -0.14
     Daly
    -0.13
    ezi
    -0.13
    tÃŃ
    -0.13
    POSITIVE LOGITS
    uw
    0.15
    enticated
    0.14
    agate
    0.14
    partment
    0.14
    leta
    0.14
    νομ
    0.13
     Dank
    0.13
    tu
    0.13
    Ïĩο
    0.13
     Tro
    0.13
    Act Density 0.223%

    No Known Activations