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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to computer programming and software development

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express a high volume of repetitive actions or tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çīĪ
    -0.72
    ģĸ
    -0.68
    ª
    -0.68
    usp
    -0.66
    Þ
    -0.64
    ablishment
    -0.64
    iphate
    -0.61
    abouts
    -0.58
    ãĥīãĥ©
    -0.58
    ŃĶ
    -0.57
    POSITIVE LOGITS
     especially
    1.21
     unless
    1.17
    unless
    1.15
    especially
    1.12
     whereas
    1.10
     so
    1.07
     hence
    1.07
     lest
    1.06
     nor
    0.99
     therefore
    0.94
    Act Density 0.299%

    No Known Activations