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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascript
    -0.17
    oir
    -0.16
    ãng
    -0.15
    hte
    -0.15
    rror
    -0.14
    stav
    -0.14
    ãĥªãĤ¢
    -0.14
    eteor
    -0.14
    viso
    -0.14
    addir
    -0.14
    POSITIVE LOGITS
     very
    0.43
    very
    0.35
     muito
    0.34
     VERY
    0.33
     sehr
    0.33
    Very
    0.33
     Very
    0.32
     bardzo
    0.31
     molto
    0.30
    VERY
    0.28
    Act Density 0.129%

    No Known Activations