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

    Neuronpedia

    INDEX
    Explanations

    instances of "prior to", "before", and "to"

    oai_token-act-pair · gemini-2.0-flash

    prior/before in time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.94
     Jefus
    -0.89
     himſelf
    -0.88
     itſelf
    -0.88
     whoſe
    -0.85
     becauſe
    -0.81
     Eſ
    -0.81
     myſelf
    -0.78
     fometimes
    -0.78
     purpoſe
    -0.78
    POSITIVE LOGITS
     before
    1.44
     Before
    1.41
    before
    1.41
    Before
    1.34
     BEFORE
    1.26
    BEFORE
    1.21
     antes
    1.18
     sebelum
    1.16
     voordat
    1.12
     πριν
    1.10
    Act Density 0.649%

    No Known Activations