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

    Neuronpedia

    INDEX
    Explanations

    references to the year 2017

    oai_token-act-pair · gpt-3.5-turbo

    references to the year 2017

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tub
    -0.81
    llular
    -0.77
    cephal
    -0.74
     drowned
    -0.68
    vere
    -0.68
    dozen
    -0.64
    chest
    -0.64
    senal
    -0.63
    gone
    -0.61
     cumbers
    -0.61
    POSITIVE LOGITS
    å¹
    0.86
    estamp
    0.80
     2017
    0.79
    âĢ²
    0.78
     ESV
    0.78
    ı
    0.71
    âĨij
    0.71
    âĢ³
    0.69
     UNHCR
    0.68
     Giov
    0.68
    Act Density 0.020%

    No Known Activations