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

    Neuronpedia

    INDEX
    Explanations

    terms related to societal and structural criticisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rchive
    -0.17
    isé
    -0.15
    ĶåĽŀ
    -0.15
    ixo
    -0.15
    ết
    -0.14
     shr
    -0.14
    олÑı
    -0.13
     ðŁĺī↵↵
    -0.13
    ioni
    -0.13
     (“
    -0.13
    POSITIVE LOGITS
    ",
    0.19
    ":
    0.18
    ":-
    0.16
    phan
    0.15
    ÙĪات
    0.15
    ":[
    0.15
    омен
    0.14
    ".
    0.14
    âĦ
    0.14
    ”,
    0.14
    Act Density 0.136%

    No Known Activations