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

    Neuronpedia

    INDEX
    Explanations

    terms related to hydration and compounds such as "hydrogen" and "hydrate."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to water and hydration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Borough
    -0.85
    éĹĺ
    -0.80
    uyomi
    -0.78
    */(
    -0.76
    ãģį
    -0.72
     Canary
    -0.70
    ourning
    -0.70
    ãĥ¯
    -0.66
    emouth
    -0.66
     Horror
    -0.65
    POSITIVE LOGITS
    rolog
    1.22
    ration
    1.18
    rol
    1.10
    rox
    1.10
    rogen
    1.06
    roph
    1.04
    rated
    0.97
    ilit
    0.96
    rop
    0.95
    rology
    0.94
    Act Density 0.014%

    No Known Activations