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

    Neuronpedia

    INDEX
    Explanations

    phrases related to endings or conclusions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the conclusion or resolution of conflicts and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.78
    ants
    -0.77
    fixes
    -0.76
    soType
    -0.70
    eous
    -0.69
    facts
    -0.69
    shapeshifter
    -0.68
    wcsstore
    -0.67
     weights
    -0.65
     cues
    -0.65
    POSITIVE LOGITS
     tenancy
    1.05
     hostilities
    1.04
     streak
    0.99
     existence
    0.92
     drought
    0.91
     misery
    0.90
     longest
    0.89
     reign
    0.89
     saga
    0.88
     relationship
    0.88
    Act Density 0.181%

    No Known Activations