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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing the intensity or nature of a situation

    oai_token-act-pair · gpt-3.5-turbo

    negative descriptions related to societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tut
    -0.52
     Tud
    -0.51
     Lincoln
    -0.48
     Milton
    -0.46
     Alto
    -0.44
     Hammond
    -0.44
     NEC
    -0.43
     Keynes
    -0.43
     ax
    -0.42
     Umb
    -0.42
    POSITIVE LOGITS
    */(
    0.79
    è¦ļéĨĴ
    0.74
    EStream
    0.67
    âĹ¼
    0.66
     ðŁij
    0.63
    .?
    0.63
    soDeliveryDate
    0.62
    ////
    0.62
    [/
    0.62
    _-
    0.60
    Act Density 2.247%

    No Known Activations