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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating purpose or direction

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a role or function

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾
    -0.72
    daq
    -0.69
    book
    -0.68
    çİĭ
    -0.65
    CV
    -0.65
    hess
    -0.65
    wa
    -0.64
    miah
    -0.64
    mare
    -0.64
    çľ
    -0.63
    POSITIVE LOGITS
     sorts
    1.00
    geries
    0.99
     constructing
    0.97
    gery
    0.95
     transmitting
    0.88
     creating
    0.87
     invading
    0.87
     acquiring
    0.87
     discovering
    0.86
     many
    0.85
    Act Density 0.183%

    No Known Activations