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

    Neuronpedia

    INDEX
    Explanations

    references to familial relationships and societal behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arded
    -0.57
    Copia
    -0.53
    culin
    -0.51
    fastjson
    -0.51
    CURS
    -0.50
    InjectAttribute
    -0.49
    eslint
    -0.49
    ⎣
    -0.47
    fml
    -0.46
    zzarella
    -0.43
    POSITIVE LOGITS
    NameInMap
    0.78
    UnusedPrivate
    0.68
     bezeichneter
    0.68
     AssemblyProduct
    0.67
    etc
    0.64
     etc
    0.64
     surtout
    0.63
     кӀ
    0.63
     respectivamente
    0.62
     للمعارف
    0.62
    Act Density 1.580%

    No Known Activations