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
    claimed
    -0.15
    ëĭ´
    -0.13
    \Array
    -0.13
     scopes
    -0.13
     EITHER
    -0.13
    orc
    -0.13
     maybe
    -0.13
     пеÑĢÑģп
    -0.13
    ÑĦоÑĢми
    -0.13
    主人
    -0.13
    POSITIVE LOGITS
     everyone
    0.33
    everyone
    0.27
     everybody
    0.27
     especially
    0.20
     tire
    0.19
     Everyone
    0.19
     thank
    0.19
    Everyone
    0.19
     entire
    0.18
     countless
    0.18
    Act Density 0.107%

    No Known Activations