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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal rights and interventions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences and variations of a specific character or symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     polyg
    -0.67
    romy
    -0.66
     fortun
    -0.64
     Niet
    -0.64
     sacrific
    -0.64
     scatter
    -0.64
     RIS
    -0.63
     conduc
    -0.62
     disclaim
    -0.62
     shack
    -0.61
    POSITIVE LOGITS
    ¹
    0.97
    ¬
    0.95
    Ī
    0.94
    ķ
    0.92
    ¡
    0.92
    ı
    0.90
    ħ
    0.90
    Ĵ
    0.86
    ª
    0.85
    atio
    0.83
    Act Density 0.260%

    No Known Activations