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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significant or transformative locations or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mb
    -0.17
     ÐĿаÑģ
    -0.15
    ccione
    -0.15
    emmel
    -0.15
     Lomb
    -0.14
    uds
    -0.14
    lsru
    -0.14
    OMB
    -0.14
    agged
    -0.14
    omb
    -0.14
    POSITIVE LOGITS
    934
    0.14
    istani
    0.14
    wang
    0.14
     Barg
    0.14
    angu
    0.14
    ohn
    0.14
    ìĹŃ
    0.13
    avit
    0.13
    959
    0.13
    625
    0.13
    Act Density 0.153%

    No Known Activations