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

    Neuronpedia

    INDEX
    Explanations

    contractions and forms of the verb "to be"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =”
    -1.11
    .’
    -1.03
    ?’
    -1.03
     ‘
    -1.01
    =’
    -1.00
    ?”
    -0.96
    ’;
    -0.94
    ’,
    -0.94
    ’.
    -0.94
    ’
    -0.93
    POSITIVE LOGITS
     lowa
    0.78
    য়ে
    0.75
     -"
    0.72
     Wordpress
    0.71
     poffe
    0.69
     ſtate
    0.69
     "
    0.69
     Moslem
    0.69
    。"
    0.68
     ftate
    0.67
    Act Density 0.527%

    No Known Activations