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
    645
    -0.18
    yk
    -0.16
     loving
    -0.16
    ayi
    -0.15
    606
    -0.15
    aldo
    -0.15
    101
    -0.15
    女åŃIJ
    -0.14
    atte
    -0.14
    725
    -0.14
    POSITIVE LOGITS
    áº
    0.15
    меÑĤÑĮ
    0.14
    LOPT
    0.14
    .mixin
    0.14
     Crest
    0.14
    ̧
    0.14
    eç
    0.14
    ró
    0.14
    ën
    0.14
    omon
    0.13
    Act Density 0.105%

    No Known Activations