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

    Neuronpedia

    INDEX
    Explanations

    references to something being concealed or hidden

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ぞれ
    -0.57
    atsu
    -0.54
    énario
    -0.51
     upper
    -0.50
     Worms
    -0.50
    sier
    -0.50
     Verhältnis
    -0.49
    foregroundColor
    -0.49
    toc
    -0.49
    М
    -0.48
    POSITIVE LOGITS
     behind
    3.21
    behind
    2.98
     Behind
    2.79
    Behind
    2.75
     BEHIND
    2.70
     derrière
    2.30
     detrás
    2.20
     dietro
    2.09
     bakom
    1.93
     achter
    1.60
    Act Density 0.066%

    No Known Activations