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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ju
    -0.60
    FilterChain
    -0.57
    andExpect
    -0.54
     raw
    -0.51
     Sa
    -0.51
     free
    -0.50
     sie
    -0.48
     ...
    -0.48
     onOptions
    -0.48
     He
    -0.47
    POSITIVE LOGITS
     myſelf
    1.13
     Monfieur
    1.11
     Shakspeare
    1.05
     itſelf
    1.04
     themſelves
    1.02
     pleaſure
    1.01
     himſelf
    1.01
     ―――――
    0.95
     Houſe
    0.94
     houſe
    0.94
    Act Density 0.899%

    No Known Activations