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

    Neuronpedia

    INDEX
    Explanations

    the word "before" and its variations used in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    KommentareTeilen
    -0.87
     habet
    -0.86
    gdx
    -0.78
     følge
    -0.75
     magasiner
    -0.70
     Talley
    -0.69
    genstein
    -0.65
    TintMode
    -0.64
    astrar
    -0.64
     casó
    -0.64
    POSITIVE LOGITS
     before
    1.74
     Before
    1.71
    before
    1.70
    BEFORE
    1.67
     BEFORE
    1.62
    Before
    1.61
     sebelum
    1.31
     πριν
    1.24
     befo
    1.24
     innan
    1.17
    Act Density 0.101%

    No Known Activations