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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences ending with the word "so."

    oai_token-act-pair · gpt-3.5-turbo

    the word "So" used as a transitional phrase

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ropolitan
    -0.64
     appeal
    -0.62
    人
    -0.62
    '>
    -0.60
    ¢
    -0.59
    idity
    -0.59
    enment
    -0.59
     AAA
    -0.59
     coincide
    -0.56
     presentation
    -0.56
    POSITIVE LOGITS
    oner
    1.16
    othes
    1.05
    ooo
    1.03
    fter
    1.03
    bered
    1.02
    oooo
    1.02
    oths
    1.02
    apy
    0.99
    othe
    0.89
    letes
    0.88
    Act Density 0.039%

    No Known Activations