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

    Neuronpedia

    INDEX
    Explanations

    references to protests and blockades in various regions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     purcha
    -0.72
     rispond
    -0.65
     embra
    -0.63
     guarante
    -0.60
     trovar
    -0.56
     wherea
    -0.56
     dilap
    -0.56
     credere
    -0.55
     scrat
    -0.54
     sputnik
    -0.54
    POSITIVE LOGITS
     blocking
    0.92
     blocked
    0.83
     Blocking
    0.74
    blocking
    0.72
     block
    0.71
    blocked
    0.70
     blocks
    0.69
     blockers
    0.68
    Blocking
    0.66
    blocker
    0.64
    Act Density 0.168%

    No Known Activations