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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases requiring specific actions or circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ANY
    -0.23
    even
    -0.20
     even
    -0.19
     anytime
    -0.18
     Anything
    -0.18
    çĶļèĩ³
    -0.18
    _ANY
    -0.18
    ä»»ä½ķ
    -0.18
     nawet
    -0.18
     Even
    -0.17
    POSITIVE LOGITS
     explicitly
    0.29
     specifically
    0.29
     accompanied
    0.28
     expressly
    0.26
    explicit
    0.25
     explicit
    0.25
    /un
    0.24
     otherwise
    0.23
     somehow
    0.23
     someone
    0.23
    Act Density 0.185%

    No Known Activations