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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names, predominantly of individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of people and places, as well as specific entities related to technology and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.67
    ufact
    -0.64
    itures
    -0.61
    pection
    -0.61
     arrest
    -0.60
     actionGroup
    -0.60
     continents
    -0.59
    hold
    -0.57
    agements
    -0.57
    past
    -0.57
    POSITIVE LOGITS
    olkien
    0.97
    onomy
    0.95
    olerance
    0.93
    uesday
    0.93
    uple
    0.92
    onga
    0.87
    itled
    0.83
    urtles
    0.81
    ribute
    0.79
    oxin
    0.76
    Act Density 0.167%

    No Known Activations