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

    Neuronpedia

    INDEX
    Explanations

    intense references to depth or profoundness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    naments
    -0.16
    onse
    -0.16
    pic
    -0.16
    abel
    -0.15
    ulumi
    -0.15
    oice
    -0.15
    que
    -0.15
    าà¸ĵ
    -0.14
    oline
    -0.14
     é¹
    -0.14
    POSITIVE LOGITS
    ening
    0.29
    ened
    0.27
     deep
    0.23
    deep
    0.19
     deeply
    0.19
    /full
    0.18
    _deep
    0.17
     Deep
    0.17
    (#)
    0.17
    /fast
    0.17
    Act Density 0.034%

    No Known Activations