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

    Neuronpedia

    INDEX
    Explanations

    references to bullets or projectiles

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     benches
    -0.84
    Diweddarwch
    -0.82
     Chry
    -0.77
    ⓧ
    -0.73
     Hap
    -0.71
    évaluateur
    -0.71
     XB
    -0.70
     Herak
    -0.70
     playstation
    -0.70
     ISNI
    -0.69
    POSITIVE LOGITS
     Bullet
    1.65
     Bullets
    1.55
    Bullet
    1.38
     BUL
    1.37
     bullet
    1.33
    bullet
    1.28
     Bulletin
    1.27
    bullets
    1.26
     Bul
    1.23
    BUL
    1.23
    Act Density 0.005%

    No Known Activations