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

    Neuronpedia

    INDEX
    Explanations

    references to discretion in decision-making processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edii
    -0.16
    infos
    -0.14
    .mixin
    -0.14
    andin
    -0.14
     Burton
    -0.14
    lum
    -0.13
    ä¹ĺ
    -0.13
    commended
    -0.13
    .IDENTITY
    -0.13
    ÑĩиÑħ
    -0.13
    POSITIVE LOGITS
     discretion
    0.55
     discret
    0.42
     judgment
    0.39
     judgement
    0.37
     sole
    0.37
     discre
    0.34
     discrete
    0.29
     Judgment
    0.28
     judgments
    0.25
    sole
    0.24
    Act Density 0.066%

    No Known Activations