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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    inar
    -0.76
    ose
    -0.70
    raq
    -0.70
    assed
    -0.68
    ¬¼
    -0.67
    alysed
    -0.67
    emaker
    -0.67
    rors
    -0.67
    rix
    -0.66
    Parameters
    -0.66
    POSITIVE LOGITS
     however
    1.05
     there
    0.99
    there
    0.97
     although
    0.84
     THERE
    0.79
     though
    0.79
     namely
    0.77
     we
    0.75
    dos
    0.71
     moreover
    0.70
    Act Density 0.107%

    No Known Activations