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

    Neuronpedia

    INDEX
    Explanations

    key identity-related phrases often associated with biographical information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itself
    -0.64
     mode
    -0.61
    GEBURTSDATUM
    -0.60
    itself
    -0.59
     "_
    -0.58
    delà
    -0.56
    '}}>
    -0.56
    ']))
    -0.55
     slow
    -0.53
    ghest
    -0.53
    POSITIVE LOGITS
     المالية
    0.62
     Ahnung
    0.61
     appointed
    0.60
     whom
    0.60
     morire
    0.58
     inoxydable
    0.57
     ASSISTANT
    0.56
     zamanda
    0.56
     youngest
    0.56
     preside
    0.56
    Act Density 0.233%

    No Known Activations