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

    Neuronpedia

    INDEX
    Explanations

    variations of the term "Po", likely referring to poetry or related subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.60
    -------
    -0.56
    TintMode
    -0.53
     <<<<<<<<<<<<<<
    -0.52
     EClass
    -0.49
    Décès
    -0.48
    GeneratedMessage
    -0.47
    TestingModule
    -0.47
     Chwiliwch
    -0.46
     tartalomajánló
    -0.46
    POSITIVE LOGITS
     Po
    0.58
    Po
    0.44
     po
    0.44
     PO
    0.39
    ensuche
    0.36
    UCE
    0.35
    EndContext
    0.34
     Beards
    0.33
    ėmis
    0.33
     poissons
    0.31
    Act Density 0.160%

    No Known Activations