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

    Neuronpedia

    INDEX
    Explanations

    phrases related to pauses or breaks

    oai_token-act-pair · gpt-3.5-turbo

    words relating to causes and effects or reasons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Yard
    -0.66
     living
    -0.64
     lantern
    -0.62
     construction
    -0.61
     Att
    -0.60
     branches
    -0.59
     wire
    -0.59
     Eisen
    -0.59
     Sapphire
    -0.58
     carp
    -0.58
    POSITIVE LOGITS
    ause
    5.05
    aughs
    1.04
    laughs
    0.99
    rompt
    0.96
    USE
    0.95
    ocalypse
    0.95
    pause
    0.94
    cause
    0.94
    aus
    0.91
    atu
    0.91
    Act Density 0.023%

    No Known Activations