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

    Neuronpedia

    INDEX
    Explanations

    action verbs related to job situations and physical actions, as well as phrases related to hardships or obstacles

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    nces
    -0.76
    CLUS
    -0.70
    DragonMagazine
    -0.67
    ITNESS
    -0.62
     hereafter
    -0.62
    urdue
    -0.61
    USER
    -0.61
    lections
    -0.61
     Letters
    -0.60
    termination
    -0.60
    POSITIVE LOGITS
     button
    0.97
     buttons
    0.96
     brakes
    0.89
     accelerator
    0.86
     punches
    0.86
     fuse
    0.85
     horn
    0.85
     drum
    0.85
     itch
    0.83
     horns
    0.82
    Act Density 1.793%

    No Known Activations