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

    Neuronpedia

    INDEX
    Explanations

    punctuation and its placement in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dit
    -0.19
    elsen
    -0.15
    alia
    -0.14
    inese
    -0.14
    urb
    -0.14
    chal
    -0.13
    entiful
    -0.13
    mpar
    -0.13
    (éĩij
    -0.13
    esda
    -0.13
    POSITIVE LOGITS
    kins
    0.15
     Levin
    0.14
    /he
    0.14
    771
    0.14
    843
    0.13
    hd
    0.13
     Robbie
    0.13
    enton
    0.13
     Markus
    0.13
    æ±
    0.12
    Act Density 0.058%

    No Known Activations