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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criticizing or mocking others

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     inherited
    -0.86
     moth
    -0.81
     occupancy
    -0.79
     abduct
    -0.78
     landsl
    -0.76
     involuntary
    -0.76
     envis
    -0.76
     corrosion
    -0.76
     strugg
    -0.75
     glim
    -0.75
    POSITIVE LOGITS
     Apparently
    1.29
     Turns
    1.29
     Needless
    1.29
     Specifically
    1.27
     Afterwards
    1.22
     Naturally
    1.21
     Seriously
    1.21
     Thankfully
    1.21
     Additionally
    1.20
     Notably
    1.19
    Act Density 0.470%

    No Known Activations