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

    Neuronpedia

    INDEX
    Explanations

    references to personal gratitude and expressions of appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     welcome
    -0.19
    welcome
    -0.19
    /welcome
    -0.18
    oller
    -0.17
     Welcome
    -0.16
    umo
    -0.16
    Welcome
    -0.16
     welcomes
    -0.15
    iesel
    -0.15
    anson
    -0.15
    POSITIVE LOGITS
     miss
    0.22
     credit
    0.19
    æ¬ł
    0.18
     wouldn
    0.17
     credits
    0.17
    miss
    0.17
     indebted
    0.17
     prive
    0.17
     misses
    0.17
     owes
    0.16
    Act Density 0.136%

    No Known Activations