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

    Neuronpedia

    INDEX
    Explanations

    words related to communication or reporting, specifically the word "said"

    oai_token-act-pair · gpt-3.5-turbo

    spoken dialogue or quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ntil
    -0.70
    Ranked
    -0.70
    pleting
    -0.68
    OSS
    -0.66
    ghazi
    -0.66
    VPN
    -0.65
    redo
    -0.65
    ²¾
    -0.64
    ading
    -0.64
    prus
    -0.64
    POSITIVE LOGITS
     goodbye
    0.97
     aloud
    0.87
    sonian
    0.80
    escription
    0.76
     sarcast
    0.75
     earlier
    0.70
    Origin
    0.68
     hello
    0.66
     publicly
    0.65
     bye
    0.65
    Act Density 0.089%

    No Known Activations