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

    Neuronpedia

    INDEX
    Explanations

    expressions related to weeks and week-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BoxFit
    -0.40
     Dorado
    -0.32
    TargetException
    -0.32
    󠁮
    -0.31
    ceutical
    -0.30
    AutoresizingMask
    -0.29
    ">>
    -0.28
     dora
    -0.28
    paddingRight
    -0.28
    figcaption
    -0.28
    POSITIVE LOGITS
    Week
    0.90
    weeks
    0.83
    week
    0.83
    nights
    0.82
     Week
    0.80
    WEEK
    0.78
     WEEK
    0.73
     week
    0.70
    Semana
    0.69
     Woche
    0.68
    Act Density 0.082%

    No Known Activations