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

    Neuronpedia

    INDEX
    Explanations

    information about organizations, locations, events, and other specific entities mentioned in documents or news articles

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     vola
    -0.70
     hek
    -0.67
     krab
    -0.65
     toilette
    -0.62
     quitt
    -0.61
     marte
    -0.61
     aquare
    -0.59
     stiller
    -0.59
     zui
    -0.57
     elek
    -0.57
    POSITIVE LOGITS
     maneu
    0.81
     shenan
    0.79
     depic
    0.78
     sophistic
    0.75
     stickied
    0.72
     accla
    0.72
     impra
    0.70
     attemp
    0.68
     upvoted
    0.67
     resemb
    0.67
    Act Density 0.872%

    No Known Activations