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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "when" in various contexts

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

    When followed by pronouns or verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IsContent
    -0.61
    EndInit
    -0.59
     ProtoMessage
    -0.56
    tagHelperRunner
    -0.55
    iddle
    -0.50
     estekak
    -0.49
    bux
    -0.48
    adget
    -0.48
    [*]
    -0.48
    nasium
    -0.47
    POSITIVE LOGITS
     WHEN
    0.59
    WHEN
    0.55
    When
    0.48
     When
    0.48
     Ketika
    0.43
    xlabel
    0.41
     VIAF
    0.40
     trampa
    0.40
     Wanneer
    0.39
     Wiesen
    0.39
    Act Density 0.024%

    No Known Activations