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

    Neuronpedia

    INDEX
    Explanations

    commands or exclamations in a conversation

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks that indicate strong emotions or commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eatures
    -0.84
     tremend
    -0.81
    avorite
    -0.76
     notor
    -0.74
     cryptoc
    -0.74
    awei
    -0.74
     controvers
    -0.74
     niche
    -0.72
     enthusi
    -0.72
    etheless
    -0.71
    POSITIVE LOGITS
     Please
    1.45
     You
    1.36
     Come
    1.35
     Didn
    1.34
     Alright
    1.34
     Explain
    1.33
     Sorry
    1.32
     Goodbye
    1.31
     Let
    1.31
     Give
    1.30
    Act Density 0.184%

    No Known Activations