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

    Neuronpedia

    INDEX
    Explanations

    phrases related to gratitude and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yles
    -0.18
     Falk
    -0.15
    ymes
    -0.14
     Benson
    -0.14
     Weston
    -0.14
     Tut
    -0.14
    ombo
    -0.14
    emoc
    -0.14
    amac
    -0.14
    Ìī
    -0.14
    POSITIVE LOGITS
    zimmer
    0.16
    ensi
    0.16
    ouri
    0.15
    arih
    0.14
    rar
    0.14
    **/↵↵
    0.14
    zu
    0.14
    uforia
    0.13
    umu
    0.13
    麻
    0.13
    Act Density 0.299%

    No Known Activations