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

    Neuronpedia

    INDEX
    Explanations

    references to various types of juices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cave
    -0.16
    (formatter
    -0.16
    *)_
    -0.15
     ActionTypes
    -0.15
    quee
    -0.15
    _TestCase
    -0.15
    atron
    -0.15
    IMS
    -0.14
    SEQ
    -0.14
    weg
    -0.14
    POSITIVE LOGITS
    overflow
    0.16
    oha
    0.15
    eric
    0.15
     Willis
    0.15
    odal
    0.14
    lobber
    0.14
     dah
    0.14
    DEFINED
    0.14
    maid
    0.14
    _defined
    0.14
    Act Density 0.002%

    No Known Activations