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

    Neuronpedia

    INDEX
    Explanations

    numerical and special characters present in the text

    oai_token-act-pair · gpt-3.5-turbo

    sequences or combinations related to food and cooking ingredients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¤ãĥĪ
    -0.62
     counterfeit
    -0.62
    illus
    -0.60
     downstream
    -0.60
    odder
    -0.59
    -+-+
    -0.58
    Kin
    -0.58
     illuminating
    -0.58
    achev
    -0.57
    ioned
    -0.56
    POSITIVE LOGITS
    ĸļ
    0.80
    otom
    0.70
    ploy
    0.69
     Ae
    0.69
    rahim
    0.67
     Cerberus
    0.66
     Cir
    0.66
    ionage
    0.66
    kson
    0.65
    ttes
    0.64
    Act Density 0.670%

    No Known Activations