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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating ongoing actions or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     comp
    -0.17
    ovsky
    -0.16
    -0.15
    onte
    -0.15
    ches
    -0.15
    λÏī
    -0.15
    ontent
    -0.14
    otech
    -0.14
    acct
    -0.14
    TU
    -0.14
    POSITIVE LOGITS
    ride
    0.15
    æĦıä¹ī
    0.14
    bject
    0.14
     ÄĮeská
    0.14
    @endif
    0.14
    pei
    0.14
    çī
    0.14
     Eval
    0.14
     GOODMAN
    0.13
    æĭ©
    0.13
    Act Density 0.025%

    No Known Activations