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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize totality or universality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     overall
    -0.21
     altogether
    -0.19
    overall
    -0.19
    ed
    -0.17
    esh
    -0.17
    ile
    -0.17
     all
    -0.16
    es
    -0.15
    ãģªãģĦ
    -0.15
    elight
    -0.15
    POSITIVE LOGITS
    igators
    0.26
    igator
    0.24
    -ÑĤаки
    0.17
    NAL
    0.17
    ignment
    0.16
    geme
    0.16
    usive
    0.15
    usions
    0.15
    oted
    0.15
    stå
    0.15
    Act Density 0.033%

    No Known Activations