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

    Neuronpedia

    INDEX
    Explanations

    terms related to exemption and exceptions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onth
    -0.15
    itori
    -0.14
    vant
    -0.14
    lej
    -0.14
    loub
    -0.14
    /text
    -0.14
    shore
    -0.13
    abin
    -0.13
    /email
    -0.13
    assi
    -0.13
    POSITIVE LOGITS
    tl
    0.19
    plied
    0.17
    alah
    0.16
    oxid
    0.15
    bye
    0.14
    oval
    0.14
    681
    0.14
    dit
    0.14
     Hancock
    0.14
    æİī
    0.14
    Act Density 0.008%

    No Known Activations