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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases that convey speech or communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    verbs of telling and saying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RetentionPolicy
    -0.59
    PMailer
    -0.59
    reportWebVitals
    -0.58
    IUrlHelper
    -0.56
    WebServlet
    -0.56
    TypedDataSet
    -0.54
    msgSender
    -0.54
    OGND
    -0.53
     kasarigan
    -0.52
    featureID
    -0.52
    POSITIVE LOGITS
     told
    0.41
     tell
    0.36
     said
    0.36
    SequentialGroup
    0.36
     say
    0.35
    GOTREF
    0.35
     promise
    0.34
    said
    0.34
     berkata
    0.33
     duquel
    0.33
    Act Density 0.041%

    No Known Activations