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

    Neuronpedia

    INDEX
    Explanations

    instances of significant numeric values and action-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uisse
    -0.16
    iá»ĩn
    -0.14
    ynn
    -0.14
     Maul
    -0.14
    YST
    -0.14
    çķª
    -0.13
    εÏĨ
    -0.13
    دÙĪ
    -0.13
    ynes
    -0.13
    ycler
    -0.13
    POSITIVE LOGITS
    bir
    0.16
    ij
    0.15
    боÑĢ
    0.15
    147
    0.15
    ria
    0.15
    angep
    0.14
    Bir
    0.14
    çuk
    0.14
     Sutton
    0.14
     Bir
    0.14
    Act Density 0.033%

    No Known Activations