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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific structured tags or entities within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bewerken
    -0.60
    SharedDtor
    -0.58
    Története
    -0.56
     चीज़ों
    -0.54
     dAtA
    -0.53
    aarrggbb
    -0.51
     astore
    -0.51
    ⓧ
    -0.46
    Lähteet
    -0.46
    DataPropertyName
    -0.45
    POSITIVE LOGITS
    __":
    0.85
    __':
    0.79
     "..\..\
    0.71
     "..\..\..\
    0.70
     Audiodateien
    0.67
    cognito
    0.67
     autorytatywna
    0.67
    Revenir
    0.65
    ocities
    0.65
    ConstraintMaker
    0.64
    Act Density 0.015%

    No Known Activations