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

    Neuronpedia

    INDEX
    Explanations

    references to personal experience and emotional states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InSection
    -0.39
    cribe
    -0.38
     MenuView
    -0.38
    \{\\
    -0.38
    annique
    -0.38
    ஢
    -0.38
     dieſes
    -0.37
    eaways
    -0.37
     ſchon
    -0.37
     cờ
    -0.37
    POSITIVE LOGITS
     himself
    0.57
    himself
    0.52
     herself
    0.51
     myself
    0.50
     ourselves
    0.48
     personally
    0.47
     propia
    0.44
     sendiri
    0.43
    herself
    0.43
    myself
    0.42
    Act Density 0.820%

    No Known Activations