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

    Neuronpedia

    INDEX
    Explanations

    numeric ranges expressed in kilometers or centimeters

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     viciss
    -0.69
    VYMaps
    -0.68
     pamph
    -0.65
     philanth
    -0.58
     OFDb
    -0.58
     Simult
    -0.57
     „,
    -0.57
     dichi
    -0.57
     practition
    -0.57
     cultur
    -0.57
    POSITIVE LOGITS
    –
    0.59
    至
    0.55
    -
    0.53
    ～
    0.50
     hanggang
    0.48
     epithe
    0.47
    oblotting
    0.46
    ajajaja
    0.46
    −
    0.45
    ถึง
    0.44
    Act Density 0.116%

    No Known Activations