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

    Neuronpedia

    INDEX
    Explanations

    phrases related to timing or conditions prior to an event

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    KommentareTeilen
    -0.92
     habet
    -0.81
    gdx
    -0.81
     Talley
    -0.75
     Messer
    -0.73
    genstein
    -0.67
     Salerno
    -0.67
    gany
    -0.66
    iestety
    -0.66
     følge
    -0.66
    POSITIVE LOGITS
    before
    1.90
     before
    1.89
    BEFORE
    1.87
     Before
    1.84
     BEFORE
    1.77
    Before
    1.74
     sebelum
    1.46
     befo
    1.40
     innan
    1.35
     πριν
    1.35
    Act Density 0.092%

    No Known Activations