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

    Neuronpedia

    INDEX
    Explanations

    phrases related to importance or impact

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating significant events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sheets
    -0.80
    units
    -0.77
    mins
    -0.77
    runs
    -0.74
    groups
    -0.72
    names
    -0.71
    books
    -0.71
     magazines
    -0.71
    classes
    -0.70
    acid
    -0.70
    POSITIVE LOGITS
     testament
    1.31
     setback
    1.25
     reminder
    1.25
     culmination
    1.22
     boon
    1.22
     continuation
    1.21
     violation
    1.17
     milestone
    1.15
     reflection
    1.12
     cornerstone
    1.11
    Act Density 0.261%

    No Known Activations