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

    Neuronpedia

    INDEX
    Explanations

    phrases related to organizations, political concepts, and rankings

    oai_token-act-pair · gpt-3.5-turbo

    terms related to governance and organizational structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ABE
    -0.76
    actionDate
    -0.68
    aples
    -0.67
    cffff
    -0.67
     Dise
    -0.66
    phalt
    -0.65
    arty
    -0.64
    姫
    -0.63
    âķIJ
    -0.63
    escription
    -0.61
    POSITIVE LOGITS
    ifier
    0.73
    naire
    0.67
    eker
    0.62
    ifiers
    0.62
    illance
    0.58
    ery
    0.58
    arians
    0.57
    arian
    0.56
    aii
    0.55
     Everest
    0.55
    Act Density 0.531%

    No Known Activations