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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and their implications in decision-making contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.49
    }))
    -0.46
     either
    -0.41
     most
    -0.41
    ckså
    -0.40
     kennis
    -0.40
     murs
    -0.40
    ismuth
    -0.40
     denke
    -0.40
     Leute
    -0.39
    POSITIVE LOGITS
    Geplaatst
    0.88
     initComponents
    0.87
    IntoConstraints
    0.80
    (!__
    0.75
    المناصب
    0.71
     himo
    0.67
     محفوظة
    0.65
     Италијани
    0.64
    AddTagHelper
    0.64
    ArrowToggle
    0.64
    Act Density 0.474%

    No Known Activations