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

    Neuronpedia

    INDEX
    Explanations

    words related to triggering actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    
    -0.78
     RouterModule
    -0.76
    fjspx
    -0.74
    存于互联网档案馆
    -0.73
    الدراسه
    -0.71
     auster
    -0.65
     insuffisamment
    -0.65
     للاسماء
    -0.63
     ModelExpression
    -0.62
     propOrder
    -0.62
    POSITIVE LOGITS
     trigger
    3.00
     Trigger
    2.73
    trigger
    2.66
     triggers
    2.62
    Trigger
    2.59
     Triggers
    2.46
     triggering
    2.34
     triggered
    2.30
     TRIG
    2.23
    triggers
    2.19
    Act Density 0.060%

    No Known Activations