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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conversational context or interjections

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

    commas and turn ends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     continúas
    -0.45
     continuant
    -0.44
    webElementGuid
    -0.44
    ArrowToggle
    -0.40
    WithIOException
    -0.40
     locura
    -0.38
     vägen
    -0.38
    calça
    -0.38
     copos
    -0.37
     mijne
    -0.36
    POSITIVE LOGITS
    참고
    0.68
    ▢
    0.52
    ValueGenerated
    0.52
    saco
    0.48
    complexContent
    0.47
     utafitiHapana
    0.47
    OCCURRED
    0.47
     EconPapers
    0.46
    Története
    0.43
    enetrable
    0.43
    Act Density 0.189%

    No Known Activations