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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a sense of role and purpose in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itore
    -0.17
     Transparency
    -0.16
    åķ
    -0.15
    ition
    -0.15
     Emerald
    -0.14
    à¥Ĥà¤ļ
    -0.14
    transparent
    -0.14
    éĢı
    -0.14
     Liberty
    -0.14
    -sensitive
    -0.14
    POSITIVE LOGITS
     typings
    0.15
    ocu
    0.15
    324
    0.14
     hist
    0.14
    гов
    0.14
     Throw
    0.14
    osemite
    0.14
    Ñİк
    0.14
    ENTA
    0.14
     網
    0.14
    Act Density 0.007%

    No Known Activations