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

    Neuronpedia

    INDEX
    Explanations

    terms that emphasize quality, value, or virtue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ense
    -0.17
    åĪ»
    -0.15
    mere
    -0.15
    /OR
    -0.14
     Mein
    -0.14
     Sadd
    -0.14
    ishi
    -0.14
    gew
    -0.14
    اسÙĬ
    -0.14
    aven
    -0.14
    POSITIVE LOGITS
    shaw
    0.18
    UNET
    0.16
    ifice
    0.15
    ediator
    0.15
    lient
    0.15
     hindsight
    0.15
    ¯u
    0.14
     Sunder
    0.14
    ific
    0.14
    cased
    0.13
    Act Density 0.058%

    No Known Activations