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

    Neuronpedia

    INDEX
    Explanations

    negations or the word "not."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ropri
    -0.15
    گر
    -0.15
    atern
    -0.14
    áºŃu
    -0.14
    \Mapping
    -0.14
    pirit
    -0.14
    би
    -0.14
    razier
    -0.14
    fiber
    -0.14
    tain
    -0.13
    POSITIVE LOGITS
     necessarily
    0.18
    kus
    0.16
    amura
    0.16
    alto
    0.16
    ches
    0.15
    elda
    0.15
    urma
    0.14
    quot
    0.14
    ulumi
    0.14
    emu
    0.14
    Act Density 0.161%

    No Known Activations