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

    Neuronpedia

    INDEX
    Explanations

    words related to different types or categories

    oai_token-act-pair · gpt-3.5-turbo

    terms that specify different types or categories of concepts and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )</
    -0.76
     shores
    -0.73
     Ruins
    -0.63
    txt
    -0.63
    oppers
    -0.63
    CHAT
    -0.62
    anwhile
    -0.62
     HOU
    -0.60
     Jah
    -0.59
    %);
    -0.59
    POSITIVE LOGITS
     guiActiveUnfocused
    0.90
     imaginable
    0.89
    iform
    0.66
     shenan
    0.65
    manship
    0.64
    ivalry
    0.63
     populism
    0.63
     intervention
    0.63
    anship
    0.61
     arrangement
    0.60
    Act Density 0.286%

    No Known Activations