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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "example" to identify illustrative references or clarifications within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Karlov
    -0.15
    tuk
    -0.15
    umbing
    -0.14
    _fds
    -0.14
    vice
    -0.14
    sz
    -0.14
    nut
    -0.14
     foreign
    -0.14
    zell
    -0.14
     Lara
    -0.14
    POSITIVE LOGITS
    IELD
    0.16
    RIORITY
    0.16
    608
    0.16
     Favor
    0.14
    leton
    0.14
    DNA
    0.14
    cool
    0.14
     hous
    0.13
     NONINFRINGEMENT
    0.13
    antt
    0.13
    Act Density 0.012%

    No Known Activations