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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the state of being alive

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riot
    -0.18
    isms
    -0.17
    mund
    -0.16
    ocker
    -0.16
    loth
    -0.15
    ét
    -0.15
    ometr
    -0.15
    list
    -0.15
    hausen
    -0.15
    missive
    -0.15
    POSITIVE LOGITS
    blood
    0.21
    è·
    0.18
    /de
    0.17
    CLE
    0.17
    flen
    0.17
    bable
    0.17
     expectancy
    0.16
    active
    0.16
    onso
    0.15
    ุà¸Ķ
    0.15
    Act Density 0.029%

    No Known Activations