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

    Neuronpedia

    INDEX
    Explanations

    phrases related to escaping or fleeing from danger

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    locker
    -0.18
    Å¡it
    -0.18
    yen
    -0.15
    iams
    -0.15
    quirer
    -0.14
    sus
    -0.14
    екÑģи
    -0.14
    xious
    -0.14
    hei
    -0.14
    hud
    -0.14
    POSITIVE LOGITS
     into
    0.20
     khá»ıi
    0.20
     hatch
    0.19
     Hatch
    0.19
     detection
    0.18
    into
    0.18
     notice
    0.18
    per
    0.16
    pell
    0.15
     reality
    0.15
    Act Density 0.024%

    No Known Activations