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

    Neuronpedia

    INDEX
    Explanations

    numeric values and their contextual significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zi
    -0.16
    anza
    -0.15
    202
    -0.15
     pap
    -0.14
    uarios
    -0.14
    816
    -0.14
    201
    -0.13
    cant
    -0.13
    artz
    -0.13
    chez
    -0.13
    POSITIVE LOGITS
    gettext
    0.16
    ãĥ³ãĤ°ãĥ«
    0.15
    åľ¨çº¿è§Ĩé¢ij
    0.14
    нии
    0.14
    ÃľM
    0.14
    ÐļÐIJ
    0.14
    wt
    0.14
    ITY
    0.14
    28
    0.13
    èĢ
    0.13
    Act Density 0.044%

    No Known Activations