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

    Neuronpedia

    INDEX
    Explanations

    punctuation and symbols used for emphasis or separation in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jefus
    -0.88
     Majefty
    -0.84
     Efq
    -0.82
     Reſ
    -0.81
     Monfieur
    -0.81
     Houſe
    -0.81
    principalTable
    -0.79
     sandero
    -0.79
     Hift
    -0.79
     ARXIV
    -0.77
    POSITIVE LOGITS
     perhaps
    0.73
     although
    0.68
     despite
    0.67
     even
    0.67
     just
    0.65
     not
    0.63
    perhaps
    0.63
    verwijspagina
    0.61
     albeit
    0.61
     but
    0.60
    Act Density 0.144%

    No Known Activations