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
    WriteAttribute
    -0.53
     Talvez
    -0.52
    出版年
    -0.51
     suivie
    -0.51
    Enllaces
    -0.50
     mukana
    -0.50
    themselves
    -0.49
     Somewhere
    -0.49
     ocurrido
    -0.49
    somewhere
    -0.49
    POSITIVE LOGITS
     very
    1.12
     again
    0.95
     muito
    0.87
    very
    0.84
     beaucoup
    0.78
     VERY
    0.78
     alot
    0.78
     mucho
    0.77
     everyone
    0.76
     guys
    0.76
    Act Density 0.081%

    No Known Activations