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

    Neuronpedia

    INDEX
    Explanations

    expressions of emotional and impulsive tendencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilip
    -0.14
    hea
    -0.13
     Delicious
    -0.13
    ahat
    -0.13
    \a
    -0.13
    elsen
    -0.13
    кÑĥÑģ
    -0.13
     Conscious
    -0.13
    ign
    -0.13
    ãĥ
    -0.13
    POSITIVE LOGITS
     intro
    0.33
     ext
    0.29
     Intro
    0.27
    intro
    0.27
     Type
    0.25
    Intro
    0.25
     outgoing
    0.24
     extrav
    0.23
     perfection
    0.21
     analytical
    0.21
    Act Density 0.108%

    No Known Activations