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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "after" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AttributeSet
    -0.92
     Efq
    -0.85
    Égypte
    -0.84
    chehen
    -0.81
    styleable
    -0.78
    BibitemShut
    -0.78
    SCAPE
    -0.76
    rillation
    -0.76
     المعيارى
    -0.74
    PhysRevD
    -0.73
    POSITIVE LOGITS
     after
    3.09
    after
    2.88
    After
    2.59
     After
    2.58
     AFTER
    2.39
    AFTER
    2.38
     dopo
    2.33
     après
    2.15
     após
    2.04
     setelah
    2.03
    Act Density 0.081%

    No Known Activations