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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal procedures and law enforcement

    oai_token-act-pair · gpt-3.5-turbo

    references to issues related to government and institutional activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     realise
    -0.88
     civilisation
    -0.83
     apologise
    -0.78
     neighbours
    -0.78
     Nato
    -0.78
     neighbouring
    -0.77
     english
    -0.76
     recognise
    -0.74
     Whilst
    -0.74
     ageing
    -0.73
    POSITIVE LOGITS
    entimes
    0.81
    typically
    0.78
    erous
    0.73
    reporting
    0.71
    bably
    0.71
     apiece
    0.71
     staffers
    0.70
    adata
    0.70
    lier
    0.69
    apter
    0.68
    Act Density 1.531%

    No Known Activations