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

    Neuronpedia

    INDEX
    Explanations

    words or characters in non-Latin scripts, particularly focusing on specific symbols and letters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     barnen
    -0.43
     politiet
    -0.41
    chieht
    -0.39
    Autoritní
    -0.36
    Puedo
    -0.34
     enfans
    -0.33
     egna
    -0.32
    Dimensões
    -0.32
    pannt
    -0.31
    なのか
    -0.31
    POSITIVE LOGITS
    󠁢
    0.69
    httphttps
    0.69
    Datuak
    0.65
    esgue
    0.60
    Zeneca
    0.56
     ErrIntOverflow
    0.55
    shortcuts
    0.52
    ]=>
    0.52
    NgModule
    0.50
     surla
    0.50
    Act Density 0.050%

    No Known Activations