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

    Neuronpedia

    INDEX
    Explanations

    references to self within code or object-oriented programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    self reference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.49
     other
    -0.45
     ['',
    -0.42
    +#+
    -0.42
     outras
    -0.41
     onCancelled
    -0.41
    xtick
    -0.41
    routeProvider
    -0.41
    {}",
    -0.40
     createTime
    -0.39
    POSITIVE LOGITS
    self
    0.98
     self
    0.87
    Self
    0.84
    SELF
    0.75
     Self
    0.74
     SELF
    0.71
    weakSelf
    0.65
     Myself
    0.65
    Myself
    0.64
     selves
    0.62
    Act Density 0.009%

    No Known Activations