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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    naments
    -0.19
    ãģ¾ãģ¾
    -0.16
    wig
    -0.15
    innacle
    -0.15
    ODO
    -0.14
    à¹īà¸ĩ
    -0.14
    erne
    -0.14
    ango
    -0.14
    otros
    -0.14
    illi
    -0.13
    POSITIVE LOGITS
    nowled
    0.18
    sgiving
    0.18
    fully
    0.17
    soever
    0.17
    yntax
    0.16
    ingly
    0.16
    fulness
    0.15
    ably
    0.14
    roup
    0.14
    orable
    0.14
    Act Density 0.031%

    No Known Activations