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

    Neuronpedia

    INDEX
    Explanations

    comparative qualities and variations in categories or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     вза
    -0.37
     bes
    -0.37
    REDU
    -0.37
     Mut
    -0.37
     Arnold
    -0.37
     Talking
    -0.36
     רצ
    -0.36
     당
    -0.36
     Egg
    -0.35
     Oester
    -0.35
    POSITIVE LOGITS
     للاسماء
    0.73
    featureID
    0.66
     soorten
    0.64
     चीज़ों
    0.63
     AssemblyCulture
    0.59
     types
    0.59
    principalColumn
    0.59
    expandindo
    0.56
     ब्रेकडाउन
    0.55
    Portály
    0.55
    Act Density 0.861%

    No Known Activations