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

    Neuronpedia

    INDEX
    Explanations

    descriptions of physical characteristics and details about individuals involved in a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     chez
    -0.16
    æĹ
    -0.15
     Protest
    -0.14
     Bilg
    -0.13
    ikt
    -0.13
    uren
    -0.13
    chn
    -0.13
     Germans
    -0.13
    onom
    -0.13
    onde
    -0.13
    POSITIVE LOGITS
     dark
    0.21
     possibly
    0.19
     medium
    0.18
     Asian
    0.18
    dark
    0.17
     Caucasian
    0.16
     unknown
    0.15
    possibly
    0.15
    Asian
    0.15
     thin
    0.15
    Act Density 0.023%

    No Known Activations