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

    Neuronpedia

    INDEX
    Explanations

    expressions related to societal and political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ikel
    -0.17
    amacare
    -0.17
    usters
    -0.16
    ãĥ¼ãĥģ
    -0.15
    erson
    -0.15
    137
    -0.15
    afone
    -0.14
     personally
    -0.14
    strup
    -0.14
    hazi
    -0.14
    POSITIVE LOGITS
    -wide
    0.24
     itself
    0.22
    wide
    0.20
     collectively
    0.19
     wide
    0.17
     Brace
    0.16
     collective
    0.16
    기ê´Ģ
    0.16
     braces
    0.16
     consensus
    0.16
    Act Density 0.146%

    No Known Activations