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

    Neuronpedia

    INDEX
    Explanations

    the presence of complex sentence structures and punctuation that indicate nuanced thought or contradictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /wiki
    -0.16
    obra
    -0.15
    esti
    -0.15
    ãģĹãĤĩ
    -0.14
    works
    -0.14
    ahr
    -0.14
    inburgh
    -0.14
    ếp
    -0.14
    mai
    -0.13
    ocop
    -0.13
    POSITIVE LOGITS
     instead
    0.28
    instead
    0.26
     Instead
    0.26
    Instead
    0.24
    Unfortunately
    0.23
     Unfortunately
    0.22
     leider
    0.21
     unfortunately
    0.20
     Sadly
    0.19
     Nope
    0.19
    Act Density 0.114%

    No Known Activations