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

    Neuronpedia

    INDEX
    Explanations

    references to physical locations or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    évaluateur
    -0.60
    COUVER
    -0.58
    httphttps
    -0.57
    oneofs
    -0.56
     ویکی‌پدیا
    -0.53
     onBind
    -0.52
     kasarigan
    -0.52
    PYX
    -0.47
    gameserver
    -0.46
     gehalten
    -0.45
    POSITIVE LOGITS
     Behind
    1.01
     behind
    1.01
     derrière
    1.00
     BEHIND
    0.97
    behind
    0.91
    Behind
    0.90
     detrás
    0.84
     bakom
    0.74
     hinter
    0.70
     Beyond
    0.70
    Act Density 0.207%

    No Known Activations