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

    Neuronpedia

    INDEX
    Explanations

    phrases related to community contributions and enrichment

    oai_token-act-pair · gpt-3.5-turbo

    concluding statements that emphasize community impact and initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unpop
    -0.76
     unre
    -0.73
     footing
    -0.71
    vag
    -0.71
     unlucky
    -0.70
    lier
    -0.67
     contraction
    -0.67
    oshenko
    -0.66
    ikuman
    -0.66
     vag
    -0.66
    POSITIVE LOGITS
     Additionally
    1.23
     However
    1.09
     Unfortunately
    1.08
     Therefore
    1.06
     Especially
    1.05
     Furthermore
    1.05
     Ultimately
    1.04
     Whilst
    1.03
     Whereas
    1.01
     Specifically
    1.01
    Act Density 1.136%

    No Known Activations