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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the addition or specifying something extra

    oai_token-act-pair · gpt-3.5-turbo

    references to additional information or benefits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Difference
    -0.72
    haw
    -0.69
     Dems
    -0.68
    izens
    -0.64
     Grape
    -0.62
    iste
    -0.62
    apego
    -0.61
     Inher
    -0.60
    ogun
    -0.59
     Pist
    -0.59
    POSITIVE LOGITS
     thereto
    0.71
    olkien
    0.70
    ĸļ
    0.66
     receiving
    0.64
    dating
    0.64
    ãģĨ
    0.62
    udes
    0.62
     materially
    0.62
    arez
    0.62
     providing
    0.62
    Act Density 0.013%

    No Known Activations