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

    Neuronpedia

    INDEX
    Explanations

    sentences that express opinions or summaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.80
    ↵
    -0.62
    ↵↵↵
    -0.50
    WebControls
    -0.50
    .
    -0.43
    ↵↵↵↵↵
    -0.43
    TestFixture
    -0.42
     schild
    -0.42
    </b>
    -0.42
     }));
    -0.41
    POSITIVE LOGITS
    verwijspagina
    0.96
    PreferredItem
    0.84
     محفوظة
    0.80
    StoryboardSegue
    0.80
    IBOutlet
    0.79
    WaitGroup
    0.78
     surla
    0.78
    Geplaatst
    0.76
     Italijani
    0.76
     سكانية
    0.75
    Act Density 0.634%

    No Known Activations