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

    Neuronpedia

    INDEX
    Explanations

    phrases related to intentions and expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.56
    entyfik
    -0.51
    forbes
    -0.50
    PRNewswire
    -0.50
    LoadMore
    -0.49
    clav
    -0.48
    Subviews
    -0.48
    toolbox
    -0.48
     rowspan
    -0.48
    而出
    -0.48
    POSITIVE LOGITS
     intention
    2.35
     intentions
    2.00
     intent
    1.96
     Intention
    1.84
    intention
    1.83
    intent
    1.50
     intenção
    1.47
     Intent
    1.46
     Inten
    1.41
     intención
    1.39
    Act Density 0.103%

    No Known Activations