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

    Neuronpedia

    INDEX
    Explanations

    phrases related to practical applications or real-world scenarios

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    :✨
    -0.69
    PARATUS
    -0.69
     CommonModule
    -0.69
    fromCharCode
    -0.68
    UserScript
    -0.66
    indexPath
    -0.65
     للمعارف
    -0.65
     незавершена
    -0.65
     utafitiHapana
    -0.65
    extAlignment
    -0.64
    POSITIVE LOGITS
    抵
    0.50
    чин
    0.50
     Clever
    0.47
    DOCTYPE
    0.47
     уте
    0.47
     Arti
    0.46
     Hydra
    0.45
    luck
    0.44
    Arti
    0.44
    Fallback
    0.44
    Act Density 0.015%

    No Known Activations