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

    Neuronpedia

    INDEX
    Explanations

    mentions of "Google" and variations of the term

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.52
    ↵
    -0.52
    <unused63>
    -0.49
    <unused61>
    -0.48
    <unused60>
    -0.47
    .
    -0.47
     ​​
    -0.47
    ↵↵
    -0.46
    ↵↵↵
    -0.46
     and
    -0.44
    POSITIVE LOGITS
    AndEndTag
    1.22
     google
    1.05
     Google
    0.98
     GOOGLE
    0.97
     Theſe
    0.96
     مرئيه
    0.93
     Monfieur
    0.92
    GOOGLE
    0.91
    Google
    0.91
    google
    0.90
    Act Density 0.138%

    No Known Activations