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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "every" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AEL
    -0.45
     Brunch
    -0.44
    kräf
    -0.42
     Jiao
    -0.42
    sld
    -0.39
     Slug
    -0.39
     STI
    -0.38
     Brandt
    -0.38
     BOC
    -0.37
     Scale
    -0.36
    POSITIVE LOGITS
    every
    1.81
     every
    1.80
     Every
    1.73
    Every
    1.72
     EVERY
    1.56
    EVERY
    1.40
    Ogni
    1.26
     setiap
    1.20
     ogni
    1.16
     Ogni
    1.11
    Act Density 0.134%

    No Known Activations