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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expressing strong disapproval or criticism

    oai_token-act-pair · gpt-3.5-turbo

    expressions of condemnation or disapproval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ramid
    -0.89
     Wonders
    -0.73
     Solitaire
    -0.70
     impro
    -0.69
    iago
    -0.68
    negie
    -0.67
     membr
    -0.66
    chn
    -0.64
    aldo
    -0.64
    hack
    -0.63
    POSITIVE LOGITS
     condemn
    0.92
     condemning
    0.87
    urous
    0.80
     harshly
    0.78
     condemnation
    0.77
     condemns
    0.77
    ations
    0.76
     unres
    0.75
     homophobic
    0.74
     denounce
    0.72
    Act Density 0.039%

    No Known Activations