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

    Neuronpedia

    INDEX
    Explanations

    phrases that challenge societal norms or highlight moral dilemmas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oldt
    -0.17
    yer
    -0.15
    croft
    -0.15
     Ut
    -0.15
    isted
    -0.14
    chers
    -0.14
    ìĤ¬ëĬĶ
    -0.14
    ãĥ³ãĥķ
    -0.14
    borough
    -0.13
    .googleapis
    -0.13
    POSITIVE LOGITS
     diseñador
    0.18
    oon
    0.14
    ily
    0.14
    occo
    0.14
    iew
    0.14
    é¤
    0.14
    itar
    0.14
     Bonnie
    0.14
    nder
    0.14
     NÄĽm
    0.13
    Act Density 0.144%

    No Known Activations