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

    Neuronpedia

    INDEX
    Explanations

    forms of the verbs "did" and "does"

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     done
    -0.86
     conducted
    -0.75
     work
    -0.75
    CompilerServices
    -0.72
     performed
    -0.71
    WriteTagHelper
    -0.71
     special
    -0.71
    раздо
    -0.70
    performed
    -0.69
     MotionEvent
    -0.69
    POSITIVE LOGITS
    ScopeManager
    0.71
     Dispens
    0.63
    JspWriter
    0.63
     TextInputType
    0.62
     المعيارى
    0.62
    expandindo
    0.61
    aság
    0.60
    SequentialGroup
    0.60
    WebControls
    0.60
     assertion
    0.59
    Act Density 0.076%

    No Known Activations