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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of "rigor" or strictness

    oai_token-act-pair · gpt-3.5-turbo

    references to rigging and related mechanical aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Peninsula
    -0.71
     Hots
    -0.71
     Faul
    -0.69
     Upton
    -0.68
     Apostle
    -0.66
     Franch
    -0.65
     corpus
    -0.64
    terson
    -0.63
     Leilan
    -0.63
    kHz
    -0.63
    POSITIVE LOGITS
    orously
    1.70
    idity
    1.18
    rig
    1.13
    gers
    1.13
    yrinth
    1.03
    ging
    1.00
    idation
    0.98
    inally
    0.97
    ged
    0.96
    etric
    0.95
    Act Density 0.029%

    No Known Activations