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

    Neuronpedia

    INDEX
    Explanations

    discourse markers that indicate contrast or transitions in arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rant
    -0.16
    -in
    -0.15
    oons
    -0.15
    strstr
    -0.14
    thur
    -0.14
    wayne
    -0.14
    warts
    -0.13
    ÙĪÙĨÙĩ
    -0.13
    ottes
    -0.13
    .addRow
    -0.13
    POSITIVE LOGITS
     ÙĪÙģÙĬ
    0.25
     During
    0.22
     during
    0.21
     In
    0.20
    During
    0.19
     At
    0.19
     On
    0.18
    ï¼Įåľ¨
    0.18
    åľ¨åľ°
    0.18
    during
    0.17
    Act Density 0.254%

    No Known Activations