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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases that imply causation or consequence

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

    Comes before question words or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    cause and effect relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    izarse
    -0.52
    投入
    -0.51
     herself
    -0.50
    私が
    -0.46
     himself
    -0.45
    了我
    -0.44
    kla
    -0.43
    Kino
    -0.43
    了他
    -0.43
     henne
    -0.42
    POSITIVE LOGITS
    tagHelper
    0.77
     things
    0.71
    bootstrapcdn
    0.70
     CreateTagHelper
    0.70
    onView
    0.68
     EconPapers
    0.68
     unknownFields
    0.68
     '{@
    0.66
    SequentialGroup
    0.66
    httphttps
    0.65
    Act Density 0.677%

    No Known Activations