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

    Neuronpedia

    INDEX
    Explanations

    themes related to incarceration and the experiences of inmates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iddles
    -0.15
    ispens
    -0.15
    ê´
    -0.15
     пÑĢоиз
    -0.15
    echa
    -0.15
    alker
    -0.15
    ãĤ¸ãĤª
    -0.14
     conventions
    -0.14
    ÑĢон
    -0.14
    ederation
    -0.14
    POSITIVE LOGITS
    265
    0.16
     Valent
    0.15
    ynamo
    0.14
     cro
    0.14
    ãĤªãĥª
    0.14
     inside
    0.14
    lon
    0.14
     Valentine
    0.13
     Inside
    0.13
     Mand
    0.13
    Act Density 0.064%

    No Known Activations