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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing depth and complexity of thought or emotion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ighbors
    -0.16
     Spl
    -0.14
    ahlen
    -0.14
     spl
    -0.14
     dri
    -0.14
    æ¡
    -0.14
    fst
    -0.13
    elf
    -0.13
    essor
    -0.13
    421
    -0.13
    POSITIVE LOGITS
     deep
    0.24
    deep
    0.22
     Deep
    0.20
     deepest
    0.20
    Deep
    0.19
     deeper
    0.19
    jian
    0.19
     DeepCopy
    0.18
    essler
    0.18
    _deep
    0.18
    Act Density 0.064%

    No Known Activations