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

    Neuronpedia

    INDEX
    Explanations

    instances of consequences or decisive actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enheim
    -0.20
    enties
    -0.17
    ätz
    -0.15
     besides
    -0.15
    èµ¢
    -0.14
    ugin
    -0.14
    ĨĴ
    -0.14
    unger
    -0.14
    tml
    -0.13
    INGLE
    -0.13
    POSITIVE LOGITS
     rather
    0.26
     upon
    0.25
     feeling
    0.24
     Rather
    0.23
    Rather
    0.22
     instead
    0.21
     Upon
    0.20
    Upon
    0.20
     after
    0.20
     knowing
    0.20
    Act Density 0.291%

    No Known Activations