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

    Neuronpedia

    INDEX
    Explanations

    phrases related to planning or activities

    oai_token-act-pair · gpt-3.5-turbo

    periods at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itely
    -0.74
     due
    -0.73
     disadvantage
    -0.72
     carbohyd
    -0.72
    itionally
    -0.69
    ascus
    -0.68
    bara
    -0.67
    vice
    -0.67
     transition
    -0.65
    ima
    -0.65
    POSITIVE LOGITS
     Anything
    1.39
     Whatever
    1.31
     Everywhere
    1.27
     Somewhere
    1.24
     And
    1.22
     Nope
    1.20
     Lots
    1.20
     Something
    1.20
     Nothing
    1.20
     Everything
    1.17
    Act Density 0.238%

    No Known Activations