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

    Neuronpedia

    INDEX
    Explanations

    phrases that discuss legal language or instructions related to statutes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    клопе
    -0.74
     typelib
    -0.74
    InjectAttribute
    -0.69
     Audiodateien
    -0.68
    CrossRef
    -0.65
     الحره
    -0.64
     تضيفلها
    -0.64
    Hochspringen
    -0.60
    InSection
    -0.60
     Wherefore
    -0.59
    POSITIVE LOGITS
     wording
    0.59
    tmpl
    0.52
    theim
    0.51
     Monaghan
    0.49
    Tikang
    0.48
     D
    0.47
    currentColor
    0.47
     stuck
    0.47
    Logan
    0.47
     nông
    0.47
    Act Density 0.019%

    No Known Activations