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

    Neuronpedia

    INDEX
    Explanations

    terms related to improvement, advancement, or enhancement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to improvements or enhancements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ships
    -0.88
    oused
    -0.76
    fuck
    -0.74
    fell
    -0.73
    wered
    -0.71
    breakers
    -0.71
    Ĭ
    -0.70
    tree
    -0.70
    coins
    -0.70
    į
    -0.69
    POSITIVE LOGITS
     versions
    0.92
     version
    0.87
     interrogation
    0.79
     scrutiny
    0.78
     senses
    0.78
     susceptibility
    0.76
     edition
    0.75
     incidence
    0.72
     capability
    0.72
     bargaining
    0.71
    Act Density 0.097%

    No Known Activations