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

    Neuronpedia

    INDEX
    Explanations

    phrases related to different professional or technical fields

    oai_token-act-pair · gpt-3.5-turbo

    references to contrasting viewpoints or differing perspectives in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĥª
    -0.56
    cellaneous
    -0.55
    staking
    -0.54
     guessed
    -0.53
    aldo
    -0.52
    tar
    -0.52
    cffffcc
    -0.51
    ighty
    -0.51
    ctory
    -0.50
    ICLE
    -0.50
    POSITIVE LOGITS
     anymore
    0.72
     anytime
    0.64
    instead
    0.61
     someday
    0.57
     extrater
    0.55
     afterlife
    0.55
     unfairly
    0.54
     ruining
    0.53
     Instead
    0.52
    versive
    0.52
    Act Density 1.898%

    No Known Activations