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

    Neuronpedia

    INDEX
    Explanations

    symbols and characters from non-Latin scripts, particularly Cyrillic letters and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Италијани
    -0.75
     utafitiHapana
    -0.67
     Chwiliwch
    -0.67
    Datuak
    -0.63
    +#+
    -0.61
     вы
    -0.59
     PeEnEo
    -0.56
     насељу
    -0.55
    oneofs
    -0.54
    Autoritní
    -0.54
    POSITIVE LOGITS
     Gegenteil
    0.56
     trekken
    0.53
    kijken
    0.50
     reducer
    0.48
     prism
    0.47
     miniaturka
    0.47
     vertellen
    0.47
     Geſch
    0.47
     gezicht
    0.47
     directivos
    0.46
    Act Density 0.005%

    No Known Activations