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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and indicators of lists or series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -0.66
     Efq
    -0.66
     Houſe
    -0.66
     Reſ
    -0.65
     Jefus
    -0.64
     houſe
    -0.63
    principalTable
    -0.63
    ſelf
    -0.62
     Hift
    -0.61
     sandero
    -0.61
    POSITIVE LOGITS
    verwijspagina
    0.73
     perhaps
    0.68
    perhaps
    0.68
     although
    0.67
    even
    0.67
    but
    0.65
    Capítulo
    0.64
    はじめに
    0.63
    although
    0.62
    except
    0.62
    Act Density 0.140%

    No Known Activations