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

    Neuronpedia

    INDEX
    Explanations

    references to organizational structures and their duties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     färg
    -0.67
     finnas
    -0.66
     igång
    -0.65
     hendes
    -0.64
     gärna
    -0.64
     fortfarande
    -0.63
     skydd
    -0.63
     varandra
    -0.62
     skär
    -0.62
     huvud
    -0.59
    POSITIVE LOGITS
     Vikipedi
    0.63
     Photocase
    0.63
    abetes
    0.61
    ⓧ
    0.61
    stdc
    0.59
     continúas
    0.58
     exp
    0.55
    httphttps
    0.55
     Waray
    0.55
     magn
    0.55
    Act Density 1.298%

    No Known Activations