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

    Neuronpedia

    INDEX
    Explanations

    references to divine judgment and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to emotion, authority, and consequence.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Negative Logits
    enderror
    -0.61
    createServer
    -0.57
    elemField
    -0.57
     ProtoMessage
    -0.54
    aarrggbb
    -0.54
    ]=>
    -0.53
    unknownFields
    -0.52
    InjectAttribute
    -0.52
    TintMode
    -0.51
     accompagner
    -0.49
    POSITIVE LOGITS
     Efq
    0.90
     myſelf
    0.88
     ſta
    0.85
    ſelf
    0.80
     raiſ
    0.78
     themſelves
    0.78
     ſhe
    0.77
     itſelf
    0.77
     caufe
    0.77
     himſelf
    0.77
    Act Density 0.186%

    No Known Activations