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

    Neuronpedia

    INDEX
    Explanations

    references to choices, decisions, or conditions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chter
    -0.14
    äºĨä¸Ģ
    -0.14
    upal
    -0.14
    pra
    -0.14
     stuff
    -0.14
    ä¸ĬäºĨ
    -0.13
    μη
    -0.13
     different
    -0.13
     ков
    -0.13
    vo
    -0.13
    POSITIVE LOGITS
     given
    0.54
    given
    0.47
     GIVEN
    0.41
     particular
    0.40
     Given
    0.36
    _given
    0.36
    Given
    0.35
     PARTICULAR
    0.30
     particul
    0.28
     certain
    0.25
    Act Density 0.377%

    No Known Activations