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

    Neuronpedia

    INDEX
    Explanations

    words associated with quantifiable actions and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     revers
    -0.17
    adeon
    -0.16
    insky
    -0.16
    tti
    -0.15
    VML
    -0.15
    arto
    -0.15
    MenuStrip
    -0.14
    TED
    -0.14
    uba
    -0.14
     spells
    -0.14
    POSITIVE LOGITS
    oker
    0.16
    oÄŁ
    0.15
     fitte
    0.15
    cee
    0.14
    utow
    0.14
    ooth
    0.14
     Kv
    0.14
    iment
    0.14
    088
    0.14
    ih
    0.13
    Act Density 0.007%

    No Known Activations