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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "so" used as an intensifier or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Olimpia
    -0.72
     hond
    -0.68
     verific
    -0.65
    ग्री
    -0.64
     Achtung
    -0.64
     vertes
    -0.64
    ِ
    -0.64
     chops
    -0.63
    Freeman
    -0.63
    Gele
    -0.63
    POSITIVE LOGITS
     So
    1.24
    So
    1.19
     so
    1.18
     SO
    1.15
    Sooo
    1.09
     Så
    0.96
    Convey
    0.96
    so
    0.95
    SO
    0.90
     sooo
    0.88
    Act Density 0.123%

    No Known Activations