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

    Neuronpedia

    INDEX
    Explanations

    requests for audience interaction or feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    exels
    -0.17
    meric
    -0.16
    into
    -0.15
    ÑĪки
    -0.15
    amo
    -0.14
    uz
    -0.14
    azard
    -0.14
    etti
    -0.14
    rab
    -0.13
     Headquarters
    -0.13
    POSITIVE LOGITS
    alone
    0.18
     Reply
    0.18
    enan
    0.17
    Reply
    0.17
     reply
    0.17
    697
    0.17
     alone
    0.16
    acomment
    0.16
    GRE
    0.16
    uben
    0.15
    Act Density 0.008%

    No Known Activations