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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "self" in object-oriented programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.97
     betweenstory
    -0.94
     OMITBAD
    -0.92
     للمعارف
    -0.86
     Administrativna
    -0.85
     Infórmanos
    -0.84
     estekak
    -0.83
     queſta
    -0.83
    Vidite
    -0.82
     Италијани
    -0.82
    POSITIVE LOGITS
    self
    0.81
     self
    0.70
    Self
    0.59
     
    0.57
     has
    0.52
     was
    0.49
    1
    0.48
    _
    0.48
     Self
    0.48
     =
    0.45
    Act Density 0.006%

    No Known Activations