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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal reflection and emotion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oup
    -0.15
     shortly
    -0.14
     quantum
    -0.14
    ora
    -0.14
     b
    -0.14
     æ©
    -0.14
    ãģªãĤĵãģ¦
    -0.13
     Quantum
    -0.13
     pre
    -0.13
    egas
    -0.13
    POSITIVE LOGITS
    nze
    0.17
    ibur
    0.15
    ÑĥÑĩа
    0.15
    оÑģÑĮ
    0.15
    жи
    0.14
    /Internal
    0.14
     Cunning
    0.14
    -caret
    0.13
     Ðļаб
    0.13
    kem
    0.13
    Act Density 0.002%

    No Known Activations