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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and emotional connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _AA
    -0.14
    incy
    -0.14
    .idea
    -0.14
     Tubes
    -0.14
    طة
    -0.13
    AGMA
    -0.13
    á»ĭch
    -0.13
    aden
    -0.13
    Ø·ÙĦب
    -0.13
    YPE
    -0.12
    POSITIVE LOGITS
     heart
    0.95
     hearts
    0.88
     Heart
    0.76
    heart
    0.76
    -heart
    0.74
    Heart
    0.71
     Hearts
    0.69
    å¿ĥ
    0.61
     coraz
    0.59
     ÑģеÑĢд
    0.59
    Act Density 0.176%

    No Known Activations