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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating actions or intentions related to observing and clarifying

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ares
    -0.20
    alem
    -0.16
    ellas
    -0.16
    úc
    -0.15
    rim
    -0.14
    uffle
    -0.14
    åħ
    -0.14
     jet
    -0.14
    ul
    -0.14
    uz
    -0.14
    POSITIVE LOGITS
    .Automation
    0.18
    erah
    0.16
    ekim
    0.15
    venes
    0.15
    NEWS
    0.14
    pais
    0.14
    ehen
    0.13
    į°
    0.13
    ride
    0.13
    rollo
    0.13
    Act Density 0.016%

    No Known Activations