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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences where something is composed or made up of various components

    oai_token-act-pair · gpt-3.5-turbo

    terms related to composition and inclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iasm
    -0.67
    paren
    -0.65
     exting
    -0.63
     conflic
    -0.61
    ithing
    -0.61
     nose
    -0.60
    iet
    -0.60
     confir
    -0.59
     recip
    -0.59
    yl
    -0.59
    POSITIVE LOGITS
    ngth
    0.77
    bourg
    0.76
     comprising
    0.72
    Ĥª
    0.72
     comprises
    0.72
    eers
    0.70
    ropolitan
    0.70
    ãĤ©
    0.68
    owship
    0.68
    warts
    0.67
    Act Density 0.034%

    No Known Activations