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

    Neuronpedia

    INDEX
    Explanations

    references to the word "given" indicating context or premise

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

    Followed by "this," "the," "our," or "your"

    np_acts-logits-general · gemini-2.0-flash

    given conditional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -1.21
     themſelves
    -1.17
     himſelf
    -1.16
     Monfieur
    -1.06
     myſelf
    -1.06
     houſe
    -1.02
     Houſe
    -0.98
     whoſe
    -0.96
     Jefus
    -0.96
     leaſt
    -0.95
    POSITIVE LOGITS
    s
    0.56
     Given
    0.55
    n
    0.54
    ness
    0.53
    ra
    0.51
    esen
    0.50
     by
    0.50
     how
    0.50
    Given
    0.50
    van
    0.49
    Act Density 0.115%

    No Known Activations