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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to fire and combustion events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AutoresizingMask
    -0.72
    elemField
    -0.60
    parsedMessage
    -0.58
     Balk
    -0.52
     deleteUser
    -0.52
    mentaux
    -0.52
    ToUser
    -0.51
    lusst
    -0.50
    Viited
    -0.50
    енча
    -0.49
    POSITIVE LOGITS
     ignition
    0.97
     igni
    0.81
     ignited
    0.77
     sparks
    0.75
     ignite
    0.74
     Ignition
    0.72
     spark
    0.71
     embers
    0.70
     fuo
    0.69
     fire
    0.69
    Act Density 0.279%

    No Known Activations