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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks that indicate speech or quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "
    -0.83
    "
    -0.71
    '
    -0.66
     '
    -0.64
     post
    -0.58
     -
    -0.57
    -"
    -0.55
     Jagger
    -0.54
    /
    -0.54
     śnie
    -0.52
    POSITIVE LOGITS
    ,’”
    1.13
    }")
    1.06
     defaultstate
    1.02
    ]));
    1.01
     Signalez
    0.98
    .’”
    0.98
    principalColumn
    0.96
     surla
    0.95
    Tembelea
    0.95
    ),”
    0.94
    Act Density 0.133%

    No Known Activations