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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating possession or association

    oai_token-act-pair · gpt-3.5-turbo

    references to companionship and togetherness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĩãĤ£
    -0.63
    ãĥ´ãĤ¡
    -0.60
    ivably
    -0.56
    ggles
    -0.56
    ãĥĭ
    -0.55
    uncture
    -0.54
    NP
    -0.54
     plurality
    -0.54
    ceivable
    -0.53
     rupture
    -0.53
    POSITIVE LOGITS
     wherever
    1.08
     everywhere
    0.98
     whenever
    0.94
     onstage
    0.87
     downstairs
    0.77
     throughout
    0.76
     anymore
    0.75
     backstage
    0.72
     everyday
    0.72
    illac
    0.72
    Act Density 0.196%

    No Known Activations