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

    Neuronpedia

    INDEX
    Explanations

    terms related to expressing thoughts or opinions

    oai_token-act-pair · gpt-3.5-turbo

    the concept of expressing thoughts or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quartered
    -0.72
    ellen
    -0.71
     Peb
    -0.69
    assic
    -0.68
    prus
    -0.67
    oult
    -0.67
    laus
    -0.66
    bably
    -0.66
     Beir
    -0.66
    etheless
    -0.66
    POSITIVE LOGITS
     express
    1.17
    ivities
    0.91
    express
    0.91
    Express
    0.88
    iveness
    0.84
    ivity
    0.81
     expresses
    0.80
    Route
    0.76
    urance
    0.76
    furt
    0.75
    Act Density 0.007%

    No Known Activations