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

    Neuronpedia

    INDEX
    Explanations

    punctuation and structures of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orld
    -0.16
    ysa
    -0.15
    orsk
    -0.14
    OUCH
    -0.14
     prostitutas
    -0.14
    oca
    -0.14
    ysi
    -0.13
    ÑĪив
    -0.13
    uzu
    -0.13
    phia
    -0.13
    POSITIVE LOGITS
     quotes
    0.20
     Quotes
    0.17
     quote
    0.17
    quote
    0.17
    -quote
    0.16
     We
    0.16
    Quotes
    0.16
     Quote
    0.16
     Volk
    0.15
    lok
    0.15
    Act Density 0.020%

    No Known Activations