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

    Neuronpedia

    INDEX
    Explanations

    elements related to strictness or severity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ksi
    -0.18
    ariat
    -0.17
    aney
    -0.16
    iox
    -0.15
    меж
    -0.15
    LOCKS
    -0.15
    wdx
    -0.15
    Degrees
    -0.15
    ocks
    -0.14
    MESS
    -0.14
    POSITIVE LOGITS
    idity
    0.36
    ging
    0.34
     rig
    0.34
     Rig
    0.34
    ged
    0.30
    gers
    0.29
    rig
    0.28
    gs
    0.25
    ueur
    0.24
    gings
    0.24
    Act Density 0.005%

    No Known Activations