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

    Neuronpedia

    INDEX
    Explanations

    phrases related to behavior and actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to behavior or behavioral studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ially
    -0.74
    pei
    -0.71
     Roof
    -0.67
     Kits
    -0.66
    IFIED
    -0.65
    eous
    -0.65
     Wid
    -0.64
    itized
    -0.62
     pid
    -0.61
    istries
    -0.61
    POSITIVE LOGITS
    aviour
    1.62
    avior
    1.49
    aving
    1.19
    aved
    1.16
    avi
    1.11
    avin
    1.03
    av
    1.02
    aves
    1.02
    avement
    0.97
    ave
    0.91
    Act Density 0.096%

    No Known Activations