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

    Neuronpedia

    INDEX
    Explanations

    emphasized expressions of truth and authenticity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    965
    -0.18
     赤
    -0.15
    itol
    -0.15
    å¾Ģ
    -0.15
    ¡
    -0.14
    vanced
    -0.14
    ç°
    -0.14
    /info
    -0.14
    å¼±
    -0.13
    rous
    -0.13
    POSITIVE LOGITS
    -blue
    0.17
    eya
    0.15
    adle
    0.14
     believer
    0.14
     pleasure
    0.14
    nda
    0.14
    izoph
    0.14
    apon
    0.14
     bis
    0.14
    HEME
    0.13
    Act Density 0.011%

    No Known Activations