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

    Neuronpedia

    INDEX
    Explanations

    punctuation or formatting indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Zem
    -0.16
    ilip
    -0.15
    ermann
    -0.15
    onis
    -0.15
     Yunan
    -0.15
    949
    -0.14
    ãĥ¼ãĥ©
    -0.14
    à¤Ĥद
    -0.14
    andra
    -0.13
    Clo
    -0.13
    POSITIVE LOGITS
    ertools
    0.16
    clus
    0.15
    igm
    0.15
    isse
    0.14
    yun
    0.14
    maj
    0.14
     Han
    0.14
    leys
    0.14
     peÅŁ
    0.14
     Gra
    0.14
    Act Density 0.000%

    No Known Activations