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

    Neuronpedia

    INDEX
    Explanations

    references to alarms and warning systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kê
    -0.15
     Hurt
    -0.15
    ãĥ«ãĤ¯
    -0.14
     chuck
    -0.14
     chat
    -0.14
     Tele
    -0.13
    Ñĥнк
    -0.13
    mach
    -0.13
     herb
    -0.13
    rot
    -0.13
    POSITIVE LOGITS
     triggered
    0.33
    trigger
    0.33
     activation
    0.31
     trigger
    0.31
    -trigger
    0.29
     Trigger
    0.29
     activations
    0.29
     triggering
    0.29
     triggers
    0.29
    .trigger
    0.28
    Act Density 0.062%

    No Known Activations