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
    ainless
    -0.14
    ince
    -0.14
    ÏĦοÏĤ
    -0.14
     Kỳ
    -0.14
    ίο
    -0.13
     ourselves
    -0.13
    oir
    -0.13
     themselves
    -0.13
    VICES
    -0.13
    _HERE
    -0.12
    POSITIVE LOGITS
     very
    0.38
     so
    0.36
     again
    0.33
     kindly
    0.32
    very
    0.28
     VERY
    0.28
     soo
    0.28
     heaps
    0.28
     sincerely
    0.26
     SO
    0.26
    Act Density 0.047%

    No Known Activations