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

    Neuronpedia

    INDEX
    Explanations

    instances of variable assignments and class properties in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.75
    <eos>
    -0.72
     "
    -0.65
     *
    -0.65
     [
    -0.61
    ↵↵
    -0.60
     “
    -0.59
     or
    -0.55
    ↵
    -0.55
    <em>
    -0.54
    POSITIVE LOGITS
     purpoſe
    1.08
     myſelf
    1.08
     Monfieur
    1.03
     Theſe
    1.02
     itſelf
    1.01
     ſeveral
    1.00
     Jefus
    1.00
     Anſ
    0.99
     ſtate
    0.98
     themſelves
    0.98
    Act Density 0.045%

    No Known Activations