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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to politics or geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to specific places and individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uration
    -0.89
    taboola
    -0.86
    raltar
    -0.84
    urable
    -0.81
    hops
    -0.81
    rar
    -0.80
    edin
    -0.79
    rams
    -0.79
    raped
    -0.76
    erness
    -0.75
    POSITIVE LOGITS
     Leone
    0.75
     Veter
    0.73
    lings
    0.70
    pora
    0.69
     Sap
    0.68
     Viper
    0.66
     Cla
    0.64
     Mub
    0.63
     Yad
    0.63
     Reaction
    0.61
    Act Density 0.050%

    No Known Activations