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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "discourse" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rice
    -0.16
    ucchini
    -0.15
    rol
    -0.14
    apat
    -0.14
    itud
    -0.14
    479
    -0.14
    isay
    -0.14
    rocess
    -0.14
    abis
    -0.14
    nave
    -0.14
    POSITIVE LOGITS
    alach
    0.17
    太éĥİ
    0.17
    èĬĻ
    0.15
    uploaded
    0.14
    ìĮ
    0.14
    بÙĪد
    0.14
    lescope
    0.14
     Tiny
    0.14
    esa
    0.14
    caf
    0.14
    Act Density 0.004%

    No Known Activations