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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal grievances or criticisms of authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cad
    -0.49
     solubility
    -0.46
     pwd
    -0.45
     rhestr
    -0.45
    }{*}{
    -0.43
     diss
    -0.43
    いぐるみ
    -0.43
    readLine
    -0.42
     cic
    -0.42
     RAP
    -0.42
    POSITIVE LOGITS
    -------
    0.55
     chrétien
    0.49
     EconPapers
    0.49
    ↵↵↵↵↵↵
    0.48
     &___
    0.46
    ↵↵↵↵
    0.46
     réfugi
    0.46
    Filmografia
    0.45
     autocollant
    0.45
    sidemargin
    0.45
    Act Density 0.580%

    No Known Activations