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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to honor and recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vinci
    -0.16
    urge
    -0.16
    gere
    -0.16
    inesis
    -0.15
    erra
    -0.15
    ãĥĭãĥĥãĤ¯
    -0.14
    tery
    -0.14
    ÙĬ
    -0.14
    ÙĨدÙĩ
    -0.14
     keer
    -0.14
    POSITIVE LOGITS
    ably
    0.33
    ific
    0.27
    fast
    0.20
    able
    0.19
    atus
    0.19
    arily
    0.17
    arium
    0.17
    full
    0.17
    iginal
    0.17
    ABLE
    0.17
    Act Density 0.016%

    No Known Activations