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

    Neuronpedia

    INDEX
    Explanations

    terms related to rigidity and strictness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ariat
    -0.20
    aney
    -0.18
    HIP
    -0.16
    ksi
    -0.16
    меж
    -0.16
    anship
    -0.15
    ãĥ³ãĥķ
    -0.15
    antz
    -0.15
    encryption
    -0.15
    incy
    -0.15
    POSITIVE LOGITS
    idity
    0.32
     rig
    0.30
    ging
    0.29
     Rig
    0.28
    ged
    0.26
    rig
    0.25
    gs
    0.24
    aud
    0.22
    gers
    0.20
    gle
    0.20
    Act Density 0.005%

    No Known Activations