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

    Neuronpedia

    INDEX
    Explanations

    adjectives ending in 'ing' or 'ed'

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    XmlAccessType
    -0.49
    ENODEV
    -0.49
    disambiguation
    -0.44
    Cdb
    -0.43
    AutoScaleMode
    -0.43
     Dan
    -0.41
     Senator
    -0.41
    Ehrungen
    -0.39
     Volkes
    -0.39
    بيوتر
    -0.39
    POSITIVE LOGITS
     FRI
    1.08
     FRE
    1.04
     Fri
    1.03
    Fri
    0.98
     frie
    0.95
     tremb
    0.95
     fri
    0.94
     FR
    0.93
     frond
    0.93
     Fre
    0.92
    Act Density 0.122%

    No Known Activations