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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "first" as a prominent marker for introduction or emphasis in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ukone
    -0.91
     méri
    -0.83
    LEncoder
    -0.82
     Scrolls
    -0.79
    aarrggbb
    -0.78
     Krieger
    -0.77
     okuyayım
    -0.76
    woordig
    -0.75
     Magdalene
    -0.75
    zeitung
    -0.74
    POSITIVE LOGITS
    FIRST
    1.34
     First
    1.34
     FIRST
    1.27
    First
    1.20
     first
    1.05
    first
    1.00
     getFirst
    0.92
     first
    0.90
    findFirst
    0.84
    isFirst
    0.82
    Act Density 0.110%

    No Known Activations