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

    Neuronpedia

    INDEX
    Explanations

    references to reading and discussing articles or stories, particularly in a conversational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     anymore
    -0.20
     throughout
    -0.19
     now
    -0.18
     yourself
    -0.16
     until
    -0.16
    706
    -0.15
     since
    -0.15
     any
    -0.15
    imo
    -0.15
     and
    -0.15
    POSITIVE LOGITS
     someone
    0.24
     somebody
    0.23
    æŁIJ
    0.23
    someone
    0.23
    çļĦä¸Ģ个
    0.20
     somewhere
    0.20
     recently
    0.19
     alguien
    0.19
    Someone
    0.18
    recent
    0.18
    Act Density 0.669%

    No Known Activations