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

    Neuronpedia

    INDEX
    Explanations

    references to publishers

    oai_token-act-pair · gpt-3.5-turbo

    references to publishers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enei
    -0.73
    00200000
    -0.69
    bones
    -0.67
    unda
    -0.66
    ewitness
    -0.65
    ohan
    -0.65
    immer
    -0.65
    pell
    -0.65
    olit
    -0.65
    liners
    -0.65
    POSITIVE LOGITS
    lisher
    1.43
    lishing
    0.98
     Publisher
    0.82
    lishes
    0.81
    itatively
    0.80
     publishers
    0.79
     publisher
    0.78
     Seym
    0.75
     royalties
    0.71
    ished
    0.70
    Act Density 0.036%

    No Known Activations