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

    Neuronpedia

    INDEX
    Explanations

    phrases and words related to introductions and welcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oran
    -0.16
    اÙĪÙĬ
    -0.15
    evin
    -0.15
    thead
    -0.15
    ť
    -0.15
    ovnÃŃ
    -0.15
    á»ijt
    -0.15
     sight
    -0.14
    ovny
    -0.14
    거리
    -0.14
    POSITIVE LOGITS
    arti
    0.15
     Herc
    0.15
    .activate
    0.14
     Tru
    0.14
    ugu
    0.14
    usta
    0.14
    ephir
    0.14
    pulse
    0.14
    ahoma
    0.14
    343
    0.14
    Act Density 0.143%

    No Known Activations