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

    Neuronpedia

    INDEX
    Explanations

    phrases related to socio-political and economic discourse

    oai_token-act-pair · gpt-3.5-turbo

    statements of certainty or definitive conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tipped
    -0.82
    lled
    -0.81
    ributes
    -0.71
     glim
    -0.70
     gunfire
    -0.69
     mosqu
    -0.68
     sergeant
    -0.68
     sealed
    -0.68
     staggered
    -0.68
     dashboard
    -0.68
    POSITIVE LOGITS
     Hence
    1.45
     Thus
    1.43
     Therefore
    1.32
     Such
    1.25
     Examples
    1.23
     Moreover
    1.23
     Consequently
    1.22
     Furthermore
    1.20
     Accordingly
    1.17
     Secondly
    1.14
    Act Density 0.430%

    No Known Activations