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

    Neuronpedia

    INDEX
    Explanations

    themes related to conflict and contradiction within societal norms and ideologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    este
    -0.18
     Silver
    -0.15
    rep
    -0.15
     word
    -0.15
    yl
    -0.15
     intervals
    -0.15
     Nat
    -0.15
    iry
    -0.14
     nat
    -0.14
    ky
    -0.14
    POSITIVE LOGITS
    asıyla
    0.16
    /engine
    0.16
    enheim
    0.16
    çĤİ
    0.16
    uppen
    0.16
    adden
    0.15
    927
    0.15
     når
    0.15
    ìĽ
    0.15
    apus
    0.15
    Act Density 0.237%

    No Known Activations