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

    Neuronpedia

    INDEX
    Explanations

    references to motor vehicles or driving

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eners
    -0.17
    urement
    -0.17
    pt
    -0.15
    nable
    -0.14
    olation
    -0.14
    py
    -0.14
    ahan
    -0.14
     Pat
    -0.14
    rd
    -0.14
    (Py
    -0.14
    POSITIVE LOGITS
    ized
    0.18
    REM
    0.17
    оке
    0.15
    ango
    0.15
    angent
    0.15
    ceph
    0.15
    angs
    0.15
    ATIO
    0.15
    cycl
    0.15
    idade
    0.14
    Act Density 0.008%

    No Known Activations