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

    Neuronpedia

    INDEX
    Explanations

    phrases related to judgment or consequences being imposed on individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to being judged, labeled, or held accountable

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     integration
    -0.73
     convergence
    -0.73
     Stability
    -0.68
     Integration
    -0.67
     succession
    -0.65
     Reconstruction
    -0.64
     divergence
    -0.64
     Confeder
    -0.63
     unification
    -0.63
     formation
    -0.62
    POSITIVE LOGITS
     aback
    0.97
    ardless
    0.79
    anked
    0.77
    inged
    0.77
    ifferent
    0.76
    angering
    0.75
    ãĤ¼
    0.75
    ptin
    0.75
    orthy
    0.74
    otyp
    0.73
    Act Density 0.331%

    No Known Activations