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

    Neuronpedia

    INDEX
    Explanations

    phrases related to international affairs and political situations

    oai_token-act-pair · gpt-3.5-turbo

    statements or sentences that represent key points or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascus
    -0.79
     salute
    -0.78
     humour
    -0.77
    ĸļ
    -0.73
     imperson
    -0.72
     spor
    -0.71
     greeting
    -0.68
     initialization
    -0.68
     abstinence
    -0.68
     allowance
    -0.67
    POSITIVE LOGITS
     Alternatively
    1.77
     Conversely
    1.43
     Otherwise
    1.43
     Ideally
    1.40
     Moreover
    1.40
     However
    1.37
     Assuming
    1.37
     Depending
    1.34
     Such
    1.33
    Alternatively
    1.33
    Act Density 0.505%

    No Known Activations