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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criticism and backlash

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating criticism or backlash from groups or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ript
    -0.71
    oire
    -0.71
    pleted
    -0.70
    eria
    -0.70
    iris
    -0.69
    osta
    -0.68
    oby
    -0.68
    erred
    -0.68
    borgh
    -0.68
    urgy
    -0.67
    POSITIVE LOGITS
     environmentalists
    1.32
     critics
    1.32
     conservatives
    1.26
     detractors
    1.23
     progressives
    1.18
     liberals
    1.18
     commentators
    1.16
     opponents
    1.14
     proponents
    1.13
     commenters
    1.11
    Act Density 0.236%

    No Known Activations