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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments or criticisms directed toward specific individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     appre
    -0.80
     circulation
    -0.74
     exper
    -0.71
     umb
    -0.70
     aggregate
    -0.69
     plur
    -0.69
     square
    -0.68
     warranty
    -0.67
     specialization
    -0.66
     reproduction
    -0.66
    POSITIVE LOGITS
    era
    1.32
    appointed
    1.31
    inspired
    1.21
    esque
    1.18
    loving
    1.17
    induced
    1.16
    driven
    1.15
    campaign
    1.12
    Clinton
    1.10
    centered
    1.09
    Act Density 0.026%

    No Known Activations