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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decentralization or devolution of power

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of evolution or development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atton
    -0.71
     advances
    -0.67
    TPS
    -0.66
    atra
    -0.64
    andem
    -0.60
    haw
    -0.60
    rill
    -0.59
     advance
    -0.59
    ena
    -0.58
    ORTS
    -0.58
    POSITIVE LOGITS
    naire
    0.78
    olved
    0.76
    ancing
    0.74
    merce
    0.74
    ary
    0.73
    heid
    0.73
    ities
    0.73
    obyl
    0.69
    ciating
    0.69
    bleacher
    0.68
    Act Density 0.044%

    No Known Activations