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

    Neuronpedia

    INDEX
    Explanations

    words related to dialogue and communication

    oai_token-act-pair · gpt-3.5-turbo

    conversational exchanges and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ).[
    -0.76
    )."
    -0.69
    ]."
    -0.68
    )?
    -0.65
    Ļ
    -0.58
    )[
    -0.58
    )|
    -0.57
    ŀ
    -0.56
    ?).
    -0.56
    )!
    -0.55
    POSITIVE LOGITS
     Flavoring
    0.59
     mundane
    0.55
    rouse
    0.54
    piring
    0.52
    antry
    0.52
     breeze
    0.52
    enance
    0.52
    ensical
    0.51
     Deity
    0.51
    outine
    0.50
    Act Density 1.484%

    No Known Activations