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

    Neuronpedia

    INDEX
    Explanations

    words related to reduction or decline

    oai_token-act-pair · gpt-3.5-turbo

    terms related to decreasing populations or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ATT
    -0.72
    Track
    -0.70
    Tra
    -0.70
     Ven
    -0.69
     Recommend
    -0.69
     QC
    -0.68
    mot
    -0.67
    Subject
    -0.66
     Offer
    -0.65
     DK
    -0.65
    POSITIVE LOGITS
     shrinking
    2.93
     dwindling
    2.27
     shrunk
    2.19
     vanishing
    1.76
     dwind
    1.76
     disappearing
    1.52
     diminishing
    1.49
     finite
    1.41
     depleted
    1.34
    shr
    1.34
    Act Density 0.032%

    No Known Activations