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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     oprot
    -0.71
     itſelf
    -0.69
    parsedMessage
    -0.68
    cyklopedia
    -0.62
    AsUp
    -0.61
     iod
    -0.60
    RegressionTest
    -0.59
     plagioclase
    -0.58
     nephe
    -0.58
     philosop
    -0.58
    POSITIVE LOGITS
     “
    0.86
     "
    0.76
    ')}}">
    0.76
     __('
    0.74
    ]]:
    0.72
    “
    0.71
    __(/*!
    0.71
     „
    0.70
     _('
    0.70
     ”
    0.67
    Act Density 0.080%

    No Known Activations