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

    Neuronpedia

    INDEX
    Explanations

    sentences with a strong positive or negative sentiment related to various economic and social issues

    oai_token-act-pair · gpt-3.5-turbo

    sentences that discuss various aspects of development and investment issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     explan
    -0.86
     unch
    -0.81
     deity
    -0.81
     mosqu
    -0.76
     tyr
    -0.75
     defe
    -0.74
     rabbit
    -0.74
     vag
    -0.74
     surname
    -0.74
     eternity
    -0.73
    POSITIVE LOGITS
     Meanwhile
    1.26
     Additionally
    1.24
     Moreover
    1.13
     Flavoring
    1.12
     Besides
    1.08
     Ultimately
    1.06
     Currently
    1.05
     Along
    1.03
     Furthermore
    1.03
     Whereas
    1.03
    Act Density 0.801%

    No Known Activations