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

    Neuronpedia

    INDEX
    Explanations

    phrases related to societal issues and controversies

    oai_token-act-pair · gpt-3.5-turbo

    discussions surrounding social issues and critiques of societal behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stabilized
    -0.71
     recovered
    -0.71
     reunited
    -0.68
     Transition
    -0.63
     repaired
    -0.62
     awaited
    -0.61
    ocamp
    -0.61
     matured
    -0.61
    Fixed
    -0.61
    iscovered
    -0.61
    POSITIVE LOGITS
     ignores
    1.40
     violates
    1.33
     undermines
    1.21
     shouldn
    1.13
     contradicts
    1.13
     justifies
    1.01
     ought
    0.97
     begs
    0.96
     doesnt
    0.95
     constitutes
    0.95
    Act Density 0.679%

    No Known Activations