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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shi
    -0.16
    endoza
    -0.15
    indo
    -0.15
    apur
    -0.15
     whats
    -0.15
     INDIRECT
    -0.14
    /articles
    -0.14
    elerik
    -0.14
    Ñıн
    -0.13
    vik
    -0.13
    POSITIVE LOGITS
     they
    0.21
     there
    0.16
     nobody
    0.16
    aken
    0.15
    UME
    0.15
     none
    0.15
     THEY
    0.15
    they
    0.15
     we
    0.14
     They
    0.14
    Act Density 0.244%

    No Known Activations