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

    Neuronpedia

    INDEX
    Explanations

    hyperlinks

    oai_token-act-pair · gpt-3.5-turbo

    frequently referenced web links and identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stuffing
    -0.74
     accrued
    -0.73
     felon
    -0.70
     commuting
    -0.70
     distance
    -0.68
     estranged
    -0.67
     caring
    -0.66
     wealthy
    -0.64
     shopping
    -0.63
     distances
    -0.63
    POSITIVE LOGITS
    nv
    1.35
    OX
    1.31
    ZI
    1.31
    sg
    1.30
    dL
    1.29
    VK
    1.29
    vg
    1.29
    vu
    1.28
    yk
    1.27
    YC
    1.27
    Act Density 0.034%

    No Known Activations