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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases that express exceptions or requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ANY
    -0.24
     anytime
    -0.18
     SHOULD
    -0.18
    ä»»ä½ķ
    -0.17
    _ANY
    -0.17
    ãĤıãģļ
    -0.17
     nawet
    -0.15
    emplates
    -0.15
    çĶļèĩ³
    -0.15
    ruh
    -0.15
    POSITIVE LOGITS
     somehow
    0.31
     specifically
    0.27
     absolutely
    0.27
     either
    0.24
     explicitly
    0.23
     absolute
    0.22
     либо
    0.22
     Absolutely
    0.21
     expressly
    0.21
     specific
    0.20
    Act Density 0.325%

    No Known Activations