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

    Neuronpedia

    INDEX
    Explanations

    sentences with strong conclusions or assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tahoe
    -0.17
    erna
    -0.15
     Ranch
    -0.15
    lej
    -0.14
     Clemson
    -0.14
    rai
    -0.14
     Purdue
    -0.14
     Baylor
    -0.14
     Californ
    -0.14
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.14
    POSITIVE LOGITS
     Brooklyn
    0.42
     NYC
    0.38
     NYPD
    0.38
    NY
    0.38
     NY
    0.35
     Staten
    0.35
     borough
    0.34
     Queens
    0.34
     Borough
    0.33
     Bronx
    0.31
    Act Density 0.000%

    No Known Activations