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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific names such as "Jem", "Ik", or "Vishal"

    oai_token-act-pair · gpt-3.5-turbo

    references to the character Aunt Jemima

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sacrament
    -0.86
    acci
    -0.79
    ric
    -0.79
    robat
    -0.78
    ycle
    -0.74
     sacrament
    -0.73
    stadt
    -0.68
    groups
    -0.68
    olitan
    -0.67
    xia
    -0.66
    POSITIVE LOGITS
     Jem
    1.36
    awks
    0.90
    itsch
    0.81
    hak
    0.74
     Jenkins
    0.74
    sey
    0.74
    velength
    0.72
    ILA
    0.71
     Kelvin
    0.70
     Barkley
    0.70
    Act Density 0.026%

    No Known Activations