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

    Neuronpedia

    INDEX
    Explanations

    phrases that express conditionality or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    now that / as soon as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pinulongan
    -0.74
     ujednoznacz
    -0.72
    rungsseite
    -0.65
    Билгалдахарш
    -0.61
    Portale
    -0.59
    ">//
    -0.58
     jspb
    -0.57
     defaultstate
    -0.57
    -0.56
     invokingState
    -0.56
    POSITIVE LOGITS
     Sobald
    0.50
    Whenever
    0.43
     Whenever
    0.38
    Anytime
    0.37
     When
    0.36
    When
    0.36
    Когда
    0.34
     aanzien
    0.32
     Gegenstand
    0.32
     Когда
    0.32
    Act Density 0.031%

    No Known Activations