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

    Neuronpedia

    INDEX
    Explanations

    words related to speech or dialogue attribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pras
    -0.15
     deck
    -0.15
    uish
    -0.14
    ovich
    -0.14
    instein
    -0.14
    à¹Īà¸ĩà¸Ĥ
    -0.14
    oucher
    -0.14
    ullivan
    -0.14
    lund
    -0.13
    _OC
    -0.13
    POSITIVE LOGITS
    thora
    0.16
    ako
    0.15
     grades
    0.15
    ductor
    0.15
     Rings
    0.14
     Radical
    0.14
    .scalablytyped
    0.14
    /rfc
    0.14
    deps
    0.14
     Paid
    0.14
    Act Density 0.029%

    No Known Activations