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

    Neuronpedia

    INDEX
    Explanations

    expressions of self-reference and personal pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.78
     AssemblyTitle
    -0.75
     صوتيه
    -0.70
     myſelf
    -0.69
     poffible
    -0.68
    Personensuche
    -0.67
    OGND
    -0.62
     itſelf
    -0.60
     betweenstory
    -0.60
     Efq
    -0.59
    POSITIVE LOGITS
     vă
    0.62
     nos
    0.58
     haberse
    0.54
     vous
    0.54
     lhes
    0.54
     θα
    0.53
     își
    0.52
     se
    0.50
     îi
    0.50
     îl
    0.50
    Act Density 0.100%

    No Known Activations