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

    Neuronpedia

    INDEX
    Explanations

    sentences with an emphasis on abstract concepts or philosophical musings

    oai_token-act-pair · gpt-3.5-turbo

    concepts of philosophical depth or irony

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dit
    -0.79
    byter
    -0.75
    idem
    -0.75
    tenance
    -0.71
    catentry
    -0.70
    BUS
    -0.70
    MpServer
    -0.69
    KO
    -0.69
    linger
    -0.68
    vice
    -0.66
    POSITIVE LOGITS
     dwelling
    0.72
    tones
    0.70
     watching
    0.69
     Enlightenment
    0.69
     these
    0.68
    effic
    0.67
     THESE
    0.66
     knowing
    0.66
     detecting
    0.65
    adding
    0.65
    Act Density 0.209%

    No Known Activations