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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and their negations that indicate potentiality and uncertainty

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

    following "not."

    np_acts-logits-general · gemini-2.0-flash

    not happen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.47
    MessageTagHelper
    -0.45
    ⓧ
    -0.45
     Gunakan
    -0.42
     tilgjenge
    -0.42
    MemoryWarning
    -0.42
    SequentialGroup
    -0.40
     יוד
    -0.39
     Lakukan
    -0.38
     prič
    -0.38
    POSITIVE LOGITS
     be
    0.56
     happen
    0.55
     occur
    0.54
     overshadow
    0.54
     lead
    0.52
    mainAxisSize
    0.50
     come
    0.49
     helps
    0.47
     consist
    0.47
    complexContent
    0.46
    Act Density 0.684%

    No Known Activations