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

    Neuronpedia

    INDEX
    Explanations

    terms associated with evidence or support in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uen
    -0.17
     Typ
    -0.16
    imei
    -0.15
    ocz
    -0.15
    nda
    -0.15
    ³
    -0.15
    ioni
    -0.14
    ÏĦικο
    -0.14
    ubb
    -0.14
    à¹Ĥย
    -0.14
    POSITIVE LOGITS
    -trans
    0.19
    edor
    0.16
    trans
    0.16
    jam
    0.16
    idor
    0.16
    jur
    0.15
    ha
    0.15
    Trans
    0.15
     Transit
    0.15
    .Packet
    0.15
    Act Density 0.034%

    No Known Activations