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

    Neuronpedia

    INDEX
    Explanations

    references to discretion and decision-making authority within formal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edii
    -0.16
    ÑĩиÑħ
    -0.15
    andin
    -0.14
    commended
    -0.14
    .dtd
    -0.14
    ä¹ĺ
    -0.14
    .mixin
    -0.13
    otland
    -0.13
    halt
    -0.13
    aldi
    -0.13
    POSITIVE LOGITS
     discretion
    0.55
     discret
    0.42
     judgment
    0.42
     judgement
    0.40
     discre
    0.34
     sole
    0.33
     discrete
    0.30
     Judgment
    0.30
     judgments
    0.28
    åĪ¤æĸŃ
    0.26
    Act Density 0.085%

    No Known Activations