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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a comparison or relationship between two entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of pairs or groups of two entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    renheit
    -0.84
    ugu
    -0.79
    ovi
    -0.78
    annel
    -0.72
    nect
    -0.71
    iggins
    -0.71
    za
    -0.70
    asta
    -0.70
    Ô
    -0.70
    fw
    -0.68
    POSITIVE LOGITS
     halves
    1.46
     thirds
    1.24
     sides
    1.12
     sexes
    1.06
    fold
    1.04
     Kore
    0.98
     dozen
    0.91
     extremes
    0.89
     main
    0.84
     aforementioned
    0.81
    Act Density 0.057%

    No Known Activations