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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technology and data analysis

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     trovar
    -0.76
     esser
    -0.74
     michelin
    -0.70
     exorbit
    -0.70
     accla
    -0.69
     fortn
    -0.66
     encomp
    -0.66
     imparare
    -0.65
     disgra
    -0.65
     arric
    -0.65
    POSITIVE LOGITS
     kony
    0.59
     fusca
    0.57
    IntoConstraints
    0.56
    iveau
    0.56
    urance
    0.55
     cso
    0.54
     high
    0.54
     FBref
    0.52
     High
    0.52
     lele
    0.51
    Act Density 0.185%

    No Known Activations