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

    Neuronpedia

    INDEX
    Explanations

    mentions related to software upgrades

    oai_token-act-pair · gpt-3.5-turbo

    references to software upgrades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PLA
    -0.75
    ued
    -0.73
    oiler
    -0.72
    ental
    -0.71
    enth
    -0.71
    amily
    -0.71
    OTUS
    -0.70
    iatric
    -0.70
    ressed
    -0.70
    yrinth
    -0.69
    POSITIVE LOGITS
     Sins
    0.78
     Veh
    0.74
    76561
    0.72
     Angelo
    0.70
     Masquerade
    0.69
     Riy
    0.68
     Advent
    0.67
    hess
    0.67
     Engels
    0.67
     Ars
    0.66
    Act Density 0.000%

    No Known Activations