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

    Neuronpedia

    INDEX
    Explanations

    phrases related to problem-solving strategies and solutions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to solutions and methods for addressing problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ector
    -0.87
    wat
    -0.78
    jad
    -0.73
    creator
    -0.72
    moon
    -0.71
    etus
    -0.69
    izens
    -0.68
    icter
    -0.67
    eah
    -0.66
    listed
    -0.66
    POSITIVE LOGITS
     brute
    1.20
     inaction
    0.98
     persuasion
    0.96
     diplomacy
    0.94
     attrition
    0.94
     concerted
    0.93
     interventions
    0.93
     rigorous
    0.92
     sheer
    0.90
     convincing
    0.89
    Act Density 0.338%

    No Known Activations