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

    Neuronpedia

    INDEX
    Explanations

    phrases related to communication and transfer of information

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions, particularly the word "and" and phrases connecting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dynam
    -0.71
     Mahjong
    -0.66
     Panda
    -0.65
     paran
    -0.62
    Sov
    -0.62
     Pigs
    -0.61
     Dian
    -0.60
     Democr
    -0.60
     Rao
    -0.60
     Circus
    -0.59
    POSITIVE LOGITS
    rogen
    1.18
    rogens
    1.16
    nery
    0.76
    chard
    0.69
    romeda
    0.67
    mouth
    0.66
    rew
    0.66
    acl
    0.66
    âķIJ
    0.64
    =-=-
    0.64
    Act Density 0.120%

    No Known Activations