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

    Neuronpedia

    INDEX
    Explanations

    words related to collaboration or working together

    oai_token-act-pair · gpt-3.5-turbo

    terms related to labor and collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ebook
    -0.68
    washer
    -0.66
     Kitty
    -0.62
     Enlightenment
    -0.62
     Pav
    -0.61
     Alps
    -0.61
     raspberry
    -0.60
    ãĥīãĥ©ãĤ´ãĥ³
    -0.60
     Blaz
    -0.58
     Wildcats
    -0.58
    POSITIVE LOGITS
    abor
    1.34
    icult
    0.94
    atory
    0.90
    atories
    0.87
    itate
    0.84
    atorium
    0.82
    vier
    0.82
    atl
    0.81
    itated
    0.80
    icus
    0.79
    Act Density 0.007%

    No Known Activations