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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing gratitude and emotional connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yp
    -0.16
     Erot
    -0.15
    aub
    -0.15
    kö
    -0.14
    wap
    -0.14
    ænd
    -0.14
    gram
    -0.14
    ety
    -0.14
     Bil
    -0.14
    ÑĥлÑıÑĢ
    -0.14
    POSITIVE LOGITS
    occo
    0.17
     Winn
    0.16
    tica
    0.15
    åĢī
    0.15
    _DUMP
    0.15
    пов
    0.15
    lád
    0.15
    raci
    0.15
    ä¼
    0.15
    utter
    0.14
    Act Density 0.396%

    No Known Activations