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

    Neuronpedia

    INDEX
    Explanations

    references to annotations and the concept of annotating data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bes
    -0.15
    669
    -0.14
    «a
    -0.14
    аÑĢод
    -0.14
     anon
    -0.14
    /slick
    -0.14
    erm
    -0.14
     Klein
    -0.13
     tent
    -0.13
     Santos
    -0.13
    POSITIVE LOGITS
    utsch
    0.15
     Picker
    0.15
    .yy
    0.14
    ãĤ·ãĤ¢
    0.14
    esome
    0.14
    ynet
    0.14
    asca
    0.13
    ãĥ£
    0.13
    EG
    0.13
    eway
    0.13
    Act Density 0.007%

    No Known Activations