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

    Neuronpedia

    INDEX
    Explanations

    comparative structures indicating relationships between multiple factors or attributes

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

    "The more/higher, the [positive adjective/adverb]" construction

    np_acts-logits-general · gemini-2.0-flash

    the X, the Y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.58
    WinForms
    -0.56
    fjspx
    -0.53
     StatelessWidget
    -0.48
    Bakgrunnsstoff
    -0.48
    それから
    -0.47
     beginnetje
    -0.47
    iann
    -0.46
    toHave
    -0.46
    bilecek
    -0.45
    POSITIVE LOGITS
     càng
    0.87
    越
    0.76
     more
    0.73
    越是
    0.73
    越多
    0.72
     semakin
    0.71
     happier
    0.68
     越
    0.68
    越大
    0.66
    越好
    0.66
    Act Density 0.252%

    No Known Activations