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

    Neuronpedia

    INDEX
    Explanations

    conditional and temporal phrases indicating situations and circumstances

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

    conditional clauses and temporal markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OCCURRED
    -0.47
    ſelf
    -0.46
    ſelves
    -0.46
     fubject
    -0.46
     tranſ
    -0.45
     myſelf
    -0.44
    ApiModelProperty
    -0.42
     uſe
    -0.41
     Houſe
    -0.41
     ſche
    -0.40
    POSITIVE LOGITS
    Personendaten
    0.65
     Мексичка
    0.52
    InstrumentedTest
    0.51
    setupUi
    0.46
     zufolge
    0.45
    Cyfarwyddwr
    0.44
     Sä
    0.43
    urlpatterns
    0.43
    ArgumentParser
    0.42
     überzeugen
    0.42
    Act Density 0.047%

    No Known Activations