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

    Neuronpedia

    INDEX
    Explanations

    the word "after" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itecture
    -0.89
     Tun
    -0.85
    XtraGrid
    -0.80
    Bronnen
    -0.80
    SCAPE
    -0.79
     TNF
    -0.79
    leſs
    -0.79
    VIRONMENT
    -0.77
    Égypte
    -0.76
    brunnen
    -0.76
    POSITIVE LOGITS
     after
    1.90
    after
    1.87
    After
    1.79
     After
    1.73
     AFTER
    1.69
    AFTER
    1.64
     dopo
    1.54
     fter
    1.36
     Dopo
    1.36
    Dopo
    1.34
    Act Density 0.112%

    No Known Activations