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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal terms and copyright information

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and formality in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     shedding
    -0.76
     buried
    -0.72
     induct
    -0.71
     schooling
    -0.71
    ŃĶ
    -0.70
     scattered
    -0.67
     entrenched
    -0.67
     ingrained
    -0.67
     enriched
    -0.66
     instinct
    -0.66
    POSITIVE LOGITS
     Please
    1.45
     Therefore
    1.35
     Additionally
    1.31
     However
    1.27
     PLEASE
    1.26
     Otherwise
    1.21
     Alternatively
    1.20
     Unless
    1.19
     Furthermore
    1.15
     Depending
    1.15
    Act Density 0.361%

    No Known Activations