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

    Neuronpedia

    INDEX
    Explanations

    references to structures or elements above a certain threshold

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portail
    -0.78
     kasarigan
    -0.72
    riwal
    -0.66
    ril
    -0.64
    cal
    -0.63
    amarin
    -0.61
     Gilles
    -0.61
     conv
    -0.58
    릴
    -0.58
     cuales
    -0.58
    POSITIVE LOGITS
     ABOVE
    1.68
    ABOVE
    1.61
     Above
    1.53
    above
    1.50
    Above
    1.49
     above
    1.47
    bove
    1.36
     BELOW
    1.17
    dessus
    1.15
     Boven
    1.11
    Act Density 0.113%

    No Known Activations