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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate urgency or importance

    oai_token-act-pair · gpt-3.5-turbo

    punctuations and sentence-ending marks, indicating significant statements or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     synthes
    -0.85
    undai
    -0.81
     eighteenth
    -0.81
     autobi
    -0.80
    conservancy
    -0.80
     immersion
    -0.78
    etheless
    -0.75
     eighteen
    -0.75
     challeng
    -0.73
    istar
    -0.73
    POSITIVE LOGITS
     pic
    1.65
     https
    1.34
    https
    1.29
     #
    1.28
    ðŁĺ
    1.28
     @
    1.25
     —
    1.19
     "@
    1.17
     ðŁij
    1.17
     ðŁ
    1.16
    Act Density 0.248%

    No Known Activations