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

    Neuronpedia

    INDEX
    Explanations

    references to specific legal sections

    oai_token-act-pair · gpt-3.5-turbo

    references to specific legal sections and articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     destro
    -0.69
    bush
    -0.62
    tails
    -0.61
    tail
    -0.60
    projects
    -0.60
    robe
    -0.59
     Markus
    -0.57
    Russ
    -0.56
    anguages
    -0.56
     favourite
    -0.56
    POSITIVE LOGITS
     VIII
    0.94
     VII
    0.89
     III
    0.83
     1070
    0.83
     XV
    0.82
     XI
    0.81
     501
    0.81
     702
    0.80
     1861
    0.80
     §§
    0.79
    Act Density 0.050%

    No Known Activations