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

    Neuronpedia

    INDEX
    Explanations

    full stops at the end of sentences

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks that signify the end or transition in ideas or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     punishment
    -0.89
     abduct
    -0.86
     contam
    -0.83
     carbohyd
    -0.83
     detainee
    -0.82
     landfall
    -0.82
     intruder
    -0.81
     detainees
    -0.81
     glim
    -0.79
     deton
    -0.79
    POSITIVE LOGITS
     Consumers
    1.47
     Companies
    1.47
     Whereas
    1.35
    Companies
    1.30
     Increasing
    1.27
     Suddenly
    1.24
     Organizations
    1.21
     Developers
    1.18
     Especially
    1.17
     Whilst
    1.15
    Act Density 0.389%

    No Known Activations