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

    Neuronpedia

    INDEX
    Explanations

    phrases related to complex and abstract concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     برانيه
    -0.48
    awtextra
    -0.46
    éget
    -0.45
    Diweddarwch
    -0.45
    Viitteet
    -0.44
    cheme
    -0.44
    HasForeignKey
    -0.43
    脚注の使い方
    -0.43
    pyplot
    -0.43
     мело
    -0.43
    POSITIVE LOGITS
     dared
    0.74
     peligroso
    0.71
     dares
    0.70
     forbidding
    0.70
     dare
    0.70
     terrifying
    0.69
     frightening
    0.67
     cautioned
    0.66
     prohibido
    0.66
     scares
    0.66
    Act Density 0.496%

    No Known Activations