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

    Neuronpedia

    INDEX
    Explanations

    informational statements or updates about various topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate important information or things the reader should pay attention to

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hierarchical
    -0.70
     stabilization
    -0.69
     subordinates
    -0.68
     equilibrium
    -0.68
     retracted
    -0.63
     releasing
    -0.63
     advances
    -0.63
     conducts
    -0.63
     revers
    -0.62
     instituted
    -0.62
    POSITIVE LOGITS
     yourself
    0.83
     geek
    0.77
     yourselves
    0.76
     watching
    0.75
     indulge
    0.75
    audi
    0.74
    tainment
    0.74
     reading
    0.73
     binge
    0.73
     browsing
    0.72
    Act Density 0.711%

    No Known Activations