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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating potential threats or significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reembols
    -0.54
    TAINER
    -0.50
    outchouc
    -0.50
    krivning
    -0.49
    tanleria
    -0.49
    LANTA
    -0.48
     الاطلاع
    -0.48
    ICTS
    -0.48
    anium
    -0.48
     Kür
    -0.47
    POSITIVE LOGITS
     spur
    1.14
     trigger
    1.11
     prompt
    1.11
     prompting
    1.08
     spurs
    1.07
     motivate
    1.05
     inspire
    1.03
     prompts
    1.02
     stimulate
    1.01
     triggering
    1.01
    Act Density 0.645%

    No Known Activations