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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to indicators or flags of various conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    faction
    -0.15
    ئة
    -0.15
    Ñijл
    -0.15
    ORLD
    -0.15
    illance
    -0.14
    íģ¼
    -0.14
    IPH
    -0.14
    ney
    -0.14
    imson
    -0.14
    éĽ¢
    -0.14
    POSITIVE LOGITS
     ind
    0.26
     Ind
    0.25
    pend
    0.21
    eterminate
    0.20
    ustrial
    0.19
    istinguish
    0.19
    ians
    0.19
    icators
    0.19
    usty
    0.17
    igo
    0.17
    Act Density 0.022%

    No Known Activations