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

    Neuronpedia

    INDEX
    Explanations

    terms related to comparative analysis and generalizations across different groups or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.80
    HasForeignKey
    -0.79
    ReusableCell
    -0.77
    RetentionPolicy
    -0.73
    Hozzáférés
    -0.73
    IsContent
    -0.69
    SOUNDBITE
    -0.67
    tagext
    -0.66
    WriteTagHelper
    -0.66
     estekak
    -0.65
    POSITIVE LOGITS
     else
    0.55
     everywhere
    0.49
     copy
    0.47
    else
    0.47
     outside
    0.45
    Rejo
    0.44
     copias
    0.43
    copyWith
    0.42
    般
    0.42
    Copy
    0.41
    Act Density 0.508%

    No Known Activations