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

    Neuronpedia

    INDEX
    Explanations

    phrases related to feedback or comments, particularly those related to criticism and praise

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating sources of praise or criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Parallel
    -0.65
     Incarnation
    -0.65
     locks
    -0.65
    enza
    -0.65
     survives
    -0.63
     lapse
    -0.62
    interrupted
    -0.62
    inse
    -0.62
     resil
    -0.62
    Password
    -0.59
    POSITIVE LOGITS
     critics
    0.88
     passers
    0.82
     pundits
    0.79
     commenters
    0.77
     commentators
    0.77
     afar
    0.76
     audiences
    0.76
     environmentalists
    0.73
     reviewers
    0.73
     mainstream
    0.73
    Act Density 0.420%

    No Known Activations