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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a significant degree of comparison or superiority

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

    emphasis on degree

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.50
    ษา
    -0.41
     adanya
    -0.40
     expériment
    -0.39
     št
    -0.38
    CompilerServices
    -0.38
    สำ
    -0.37
     similares
    -0.36
     NgModule
    -0.36
     samme
    -0.36
    POSITIVE LOGITS
     biggest
    0.66
     strongest
    0.66
    圧倒
    0.64
     unquestionably
    0.64
    cydow
    0.63
     best
    0.63
    satunya
    0.62
    best
    0.61
     arguably
    0.61
     greatest
    0.59
    Act Density 0.016%

    No Known Activations