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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating belonging or inclusion

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of "part of" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acs
    -0.83
    culosis
    -0.68
     pestic
    -0.66
     vomit
    -0.64
     ceilings
    -0.63
     viol
    -0.62
     conduc
    -0.61
     blat
    -0.58
    Arcade
    -0.58
    reys
    -0.58
    POSITIVE LOGITS
     Scouting
    0.71
    agons
    0.63
     UNESCO
    0.62
     Geh
    0.62
    anian
    0.61
     the
    0.60
    ordinate
    0.60
    ãģĨ
    0.60
    rador
    0.59
    xon
    0.59
    Act Density 0.068%

    No Known Activations