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

    Neuronpedia

    INDEX
    Explanations

    references to the keyword "self" in code, indicating object-oriented programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     deleteUser
    -0.60
     القدم
    -0.60
    ]--;
    -0.59
    Religious
    -0.59
    AutoScaleMode
    -0.56
    Chham
    -0.55
     Packard
    -0.55
    ❹
    -0.54
    Портали
    -0.54
    PIA
    -0.54
    POSITIVE LOGITS
    self
    1.98
    selves
    1.25
    SELF
    1.00
     selves
    0.92
    Self
    0.90
     herself
    0.83
    ELF
    0.82
     بيها
    0.81
     yourself
    0.81
     Self
    0.78
    Act Density 0.063%

    No Known Activations