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
     unless
    -0.07
    asa
    -0.07
    bara
    -0.07
    unless
    -0.06
    _FE
    -0.06
    Ñĥже
    -0.06
    ald
    -0.06
    rade
    -0.06
    éĻ¤
    -0.06
    boa
    -0.06
    POSITIVE LOGITS
     behalf
    0.07
     suá»ijt
    0.07
     throughout
    0.07
    CTS
    0.07
    elm
    0.07
    anging
    0.07
     SHARES
    0.06
    عاÙĨ
    0.06
    	throws
    0.06
     tão
    0.06
    Act Density 0.056%

    No Known Activations