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

    Neuronpedia

    INDEX
    Explanations

    administrative or governing terms and actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to administrative actions and instantiation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Parish
    -0.74
     Welsh
    -0.74
     Abyss
    -0.70
     Dear
    -0.69
     Missing
    -0.68
     Waters
    -0.67
     Carrier
    -0.67
    Downloadha
    -0.66
     Spear
    -0.66
    Ô
    -0.66
    POSITIVE LOGITS
    ented
    1.04
    ents
    0.98
    itations
    0.95
    ulators
    0.94
    itating
    0.93
    sa
    0.91
    aps
    0.90
    itated
    0.90
    elled
    0.89
    isters
    0.88
    Act Density 0.094%

    No Known Activations