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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating consensus or collective agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TRACE
    -0.14
    .Yellow
    -0.14
     vag
    -0.14
    LARI
    -0.14
     applyMiddleware
    -0.14
    ettel
    -0.14
    ¸ı
    -0.13
    Ñĩини
    -0.13
    acente
    -0.13
    rack
    -0.13
    POSITIVE LOGITS
     chorus
    0.22
     consensus
    0.21
     alike
    0.19
     unanimous
    0.17
     unanimously
    0.17
     across
    0.16
     nhau
    0.16
     voices
    0.16
     agreement
    0.15
     unanim
    0.15
    Act Density 0.191%

    No Known Activations