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
    ouve
    -0.18
     Gins
    -0.15
    rat
    -0.15
    formed
    -0.15
    ark
    -0.14
    anity
    -0.14
    ãģªãģŁ
    -0.14
    олаг
    -0.14
    oked
    -0.14
    ucas
    -0.13
    POSITIVE LOGITS
     goes
    0.26
     Goes
    0.18
     reserved
    0.17
     go
    0.17
    ãģ¹ãģį
    0.16
     kepada
    0.16
    602
    0.15
     traveling
    0.15
     goto
    0.15
     Ot
    0.15
    Act Density 0.033%

    No Known Activations