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

    Neuronpedia

    INDEX
    Explanations

    references to theories and theoretical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouch
    -0.18
    mere
    -0.17
    áÄį
    -0.15
    UDGE
    -0.15
    acre
    -0.15
    etler
    -0.15
    ubo
    -0.15
    eting
    -0.15
    pcf
    -0.15
    nemonic
    -0.14
    POSITIVE LOGITS
    ERSHEY
    0.20
    /method
    0.18
    zzo
    0.17
    istically
    0.17
    ically
    0.16
    ëĮĢë¡ľ
    0.16
     же
    0.15
     dõi
    0.15
    636
    0.15
    ItemSelected
    0.15
    Act Density 0.035%

    No Known Activations