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

    Neuronpedia

    INDEX
    Explanations

    specific Polish words and phrases related to identity and origins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucch
    -0.16
    ersen
    -0.16
    wers
    -0.15
     plata
    -0.15
    sian
    -0.15
    оÑĢод
    -0.14
    OME
    -0.14
    Brun
    -0.14
     brun
    -0.14
    ucid
    -0.14
    POSITIVE LOGITS
    sez
    0.19
    .Aggressive
    0.16
    iem
    0.15
    amba
    0.14
    .Skin
    0.14
    apor
    0.14
    wis
    0.14
     cái
    0.14
     Spar
    0.14
    ante
    0.14
    Act Density 0.007%

    No Known Activations