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

    Neuronpedia

    INDEX
    Explanations

    instances of action-oriented phrases suggesting planning or execution strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.95
     Jefus
    -0.94
     Efq
    -0.94
     houſe
    -0.93
     Chriftian
    -0.92
     Diſ
    -0.92
     themſelves
    -0.91
     himſelf
    -0.91
     ſmall
    -0.90
     purpoſe
    -0.89
    POSITIVE LOGITS
     perhaps
    0.56
     fundamental
    0.54
    AddHtmlAttribute
    0.52
     such
    0.49
     clés
    0.47
     demikian
    0.47
     nă
    0.46
     referrerpolicy
    0.46
     chave
    0.46
     crucial
    0.46
    Act Density 1.080%

    No Known Activations