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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparison or quantity

    oai_token-act-pair · gpt-3.5-turbo

    the use of the word "as" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oller
    -0.62
     Mason
    -0.58
     antioxid
    -0.57
    heses
    -0.57
     Import
    -0.56
    ivals
    -0.55
     Democr
    -0.54
    POST
    -0.54
    NEY
    -0.52
    Ùĩ
    -0.51
    POSITIVE LOGITS
    pired
    1.32
    pires
    1.24
    ynchron
    1.11
    phy
    1.04
     opposed
    1.01
    pire
    0.94
    piration
    0.93
    part
    0.89
    cription
    0.89
    ym
    0.89
    Act Density 0.154%

    No Known Activations