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

    Neuronpedia

    INDEX
    Explanations

    the word "Griffin" and its variations, indicating a focus on a specific subject or entity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Manson
    -0.64
     forcé
    -0.63
     abstrato
    -0.61
    SessionFactory
    -0.61
    ophan
    -0.58
     pardon
    -0.58
     Marston
    -0.57
     sachets
    -0.57
     sachet
    -0.56
    Билгалдахарш
    -0.56
    POSITIVE LOGITS
     Gri
    1.90
    Gri
    1.80
     gri
    1.73
    gri
    1.72
     Grill
    1.33
     grill
    1.24
     grills
    1.17
    Grill
    1.16
    grill
    1.05
     grille
    0.99
    Act Density 0.062%

    No Known Activations