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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal actions and consequences

    oai_token-act-pair · gpt-3.5-turbo

    actions and events related to legal or disciplinary issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usterity
    -0.70
    phony
    -0.64
    pac
    -0.60
    arist
    -0.59
    Effect
    -0.58
    achev
    -0.56
    weed
    -0.55
    bert
    -0.55
    arn
    -0.55
    Publisher
    -0.54
    POSITIVE LOGITS
     additionally
    0.84
     withd
    0.78
     rul
    0.76
    anwhile
    0.74
     separately
    0.71
     secondly
    0.71
     again
    0.70
     ALSO
    0.70
    again
    0.70
    eatures
    0.67
    Act Density 0.656%

    No Known Activations