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

    Neuronpedia

    INDEX
    Explanations

    descriptive phrases related to shared experiences and emotional connections in social settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utterstock
    -0.80
     Shutterstock
    -0.68
    imester
    -0.67
     ®
    -0.64
    rencies
    -0.60
     Economy
    -0.60
     Gallup
    -0.59
    ģĸ
    -0.56
     Simply
    -0.56
     paradox
    -0.56
    POSITIVE LOGITS
     stuff
    0.99
     etc
    0.97
     blah
    0.95
     respectively
    0.84
     shit
    0.82
     fuckin
    0.81
     demos
    0.81
     haha
    0.77
    entimes
    0.75
     goodies
    0.75
    Act Density 0.357%

    No Known Activations