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

    Neuronpedia

    INDEX
    Explanations

    phrases where an object or concept is physically connected or attached to something else

    oai_token-act-pair · gpt-3.5-turbo

    instances of phrases indicating attachment or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esi
    -0.73
    RD
    -0.72
    urg
    -0.71
    incinn
    -0.70
    TPPStreamerBot
    -0.68
    emetery
    -0.68
    Champ
    -0.66
    anchester
    -0.65
    hur
    -0.65
    orders
    -0.65
    POSITIVE LOGITS
    othy
    0.80
     handle
    0.72
    ggles
    0.71
     conserve
    0.71
     compensate
    0.71
     shore
    0.71
     preserve
    0.70
     ensure
    0.69
     insure
    0.69
    ffee
    0.69
    Act Density 0.165%

    No Known Activations