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

    Neuronpedia

    INDEX
    Explanations

    references to models and modeling in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isi
    -0.15
    eteria
    -0.15
    dar
    -0.15
    vert
    -0.14
    anela
    -0.14
    ï¸
    -0.14
     neutral
    -0.14
     luáºŃn
    -0.13
    åĩĢ
    -0.13
    à¥ĩद
    -0.13
    POSITIVE LOGITS
    -model
    0.15
    UBY
    0.14
    641
    0.14
    Fizz
    0.14
     Swarm
    0.14
    Republic
    0.14
    urve
    0.14
    642
    0.13
    contres
    0.13
    ritte
    0.13
    Act Density 0.014%

    No Known Activations