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

    Neuronpedia

    INDEX
    Explanations

    references to social media or digital communication roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Biden
    -0.13
     Hollywood
    -0.13
     Pulitzer
    -0.13
     millions
    -0.13
    .cert
    -0.13
     Birmingham
    -0.13
    inent
    -0.13
     forensic
    -0.12
     billions
    -0.12
     heavyweight
    -0.12
    POSITIVE LOGITS
     Shar
    0.36
    Shar
    0.32
     Math
    0.30
     Maths
    0.28
     village
    0.28
     villagers
    0.28
    Math
    0.26
    .Math
    0.25
     Sharp
    0.24
     Village
    0.22
    Act Density 0.002%

    No Known Activations