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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and support from people

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and words indicating collective experiences or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Enlarge
    -0.67
    ":"/
    -0.66
     Prohibition
    -0.63
    ":["
    -0.60
    null
    -0.60
    DX
    -0.59
    rine
    -0.58
    2020
    -0.58
    ENSE
    -0.58
    aq
    -0.57
    POSITIVE LOGITS
    been
    1.50
     gotten
    1.30
     been
    1.23
     gone
    1.22
     risen
    1.07
     eaten
    1.05
     fallen
    1.03
     begun
    1.00
     undergone
    0.99
     done
    0.98
    Act Density 0.499%

    No Known Activations