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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating timeframes and durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    942
    -0.19
    861
    -0.15
    ãĥ³ãĥĦ
    -0.15
    SSF
    -0.15
    igne
    -0.15
    extras
    -0.14
    921
    -0.14
     micron
    -0.14
     submerged
    -0.14
    erva
    -0.14
    POSITIVE LOGITS
    amedi
    0.16
    contra
    0.16
    idad
    0.15
    ãĤ«ãĥ¼
    0.15
     Impl
    0.14
    ñana
    0.14
     GenerationType
    0.14
    änn
    0.14
    ãĥ³ãĥĸ
    0.14
     пÑĢедел
    0.14
    Act Density 0.076%

    No Known Activations