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

    Neuronpedia

    INDEX
    Explanations

    assignment operators or variable initializations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     -
    -0.71
     (
    -0.70
     Road
    -0.69
     "
    -0.65
     –
    -0.63
     
    -0.63
     I
    -0.62
     :
    -0.61
     +
    -0.61
     //
    -0.60
    POSITIVE LOGITS
     pleaſure
    1.55
     raiſ
    1.50
     Jefus
    1.45
     myſelf
    1.44
     itſelf
    1.43
     whoſe
    1.40
     themſelves
    1.38
     poffible
    1.37
     uſed
    1.37
     houſe
    1.36
    Act Density 0.140%

    No Known Activations