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

    Neuronpedia

    INDEX
    Explanations

    information regarding planned projects and ongoing developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alm
    -0.15
    shan
    -0.14
     ad
    -0.14
    iry
    -0.14
    ibal
    -0.14
     conce
    -0.14
     Jama
    -0.13
     adm
    -0.13
    246
    -0.13
     Alive
    -0.13
    POSITIVE LOGITS
     Roose
    0.19
    ãĥ¼ãĥĨ
    0.16
    uale
    0.16
    OffsetTable
    0.16
    atedRoute
    0.15
    itler
    0.15
    ertools
    0.15
    erdem
    0.15
    PRI
    0.15
    ONO
    0.15
    Act Density 0.208%

    No Known Activations