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

    Neuronpedia

    INDEX
    Explanations

    affirmations and expressions of self-identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulton
    -0.18
    heck
    -0.16
    име
    -0.16
    oled
    -0.15
    hea
    -0.15
    ij¸
    -0.15
    IRON
    -0.15
    eya
    -0.15
    ÏģÏī
    -0.14
    ylon
    -0.14
    POSITIVE LOGITS
     now
    0.16
    eld
    0.14
     merely
    0.14
     atr
    0.14
    anda
    0.14
     thanks
    0.14
    uco
    0.14
     mere
    0.14
     fare
    0.14
     eig
    0.14
    Act Density 0.002%

    No Known Activations