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

    Neuronpedia

    INDEX
    Explanations

    mentions of trainers and training-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hus
    -0.18
    ersh
    -0.16
    /pm
    -0.15
    endregion
    -0.15
    orges
    -0.15
    ÑĸÑĪ
    -0.14
    jerne
    -0.14
    rum
    -0.14
    RIORITY
    -0.14
    ushman
    -0.14
    POSITIVE LOGITS
    dio
    0.17
     Sent
    0.15
    uide
    0.15
    atical
    0.15
    vail
    0.15
     SENT
    0.14
    átka
    0.14
    mute
    0.14
    çĿĢ
    0.14
     Bite
    0.14
    Act Density 0.003%

    No Known Activations