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

    Neuronpedia

    INDEX
    Explanations

    references to eventual outcomes or conclusions in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows the word "eventually"

    np_acts-logits-general · gemini-2.0-flash

    eventually followed by action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     immediately
    -1.04
     initially
    -1.02
    immediately
    -1.00
     inmediatamente
    -0.99
     immediate
    -0.98
     previously
    -0.96
     immédiatement
    -0.96
    mediately
    -0.95
    previously
    -0.93
     imediatamente
    -0.93
    POSITIVE LOGITS
     تضيفلها
    0.76
     rospy
    0.60
    AndEndTag
    0.60
     succumb
    0.59
     متعلقه
    0.59
     became
    0.58
     realized
    0.57
     realizing
    0.56
     realize
    0.56
     convinced
    0.56
    Act Density 0.226%

    No Known Activations