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

    Neuronpedia

    INDEX
    Explanations

    names of universities

    oai_token-act-pair · gpt-3.5-turbo

    references to universities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lda
    -0.75
    adow
    -0.73
    nir
    -0.70
    elist
    -0.67
    TPS
    -0.65
    ppings
    -0.65
    othy
    -0.64
    meaning
    -0.63
    gone
    -0.62
    trap
    -0.61
    POSITIVE LOGITS
    uates
    0.93
     Extension
    0.90
     Libraries
    0.90
     Hospital
    0.83
     College
    0.81
    essor
    0.80
    ĨĴ
    0.79
    Hum
    0.79
     Hosp
    0.78
     Registrar
    0.77
    Act Density 0.034%

    No Known Activations