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

    Neuronpedia

    INDEX
    Explanations

    expressions of love and admiration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     @"/
    -0.68
     "..\..\
    -0.62
     تانيه
    -0.62
    MLLoader
    -0.60
     "..\..\..\
    -0.59
    المناصب
    -0.59
     getRule
    -0.58
    NewReader
    -0.58
    cyklopedia
    -0.58
    PerformLayout
    -0.57
    POSITIVE LOGITS
     autorytatywna
    0.54
     än
    0.45
     vostri
    0.41
     automatiques
    0.41
    tiek
    0.40
    inerja
    0.39
     onData
    0.39
    ệu
    0.38
    انجليز
    0.38
     suena
    0.37
    Act Density 0.084%

    No Known Activations