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

    Neuronpedia

    INDEX
    Explanations

    statements that introduce or emphasize a subject or concept

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ally
    -0.15
     endors
    -0.14
    ouz
    -0.14
    .ly
    -0.14
    elpers
    -0.14
    ìĶ©
    -0.14
    ombat
    -0.14
    ald
    -0.14
    oom
    -0.14
    ings
    -0.14
    POSITIVE LOGITS
    mia
    0.15
    coma
    0.15
    ̣
    0.15
    -scalable
    0.14
    éry
    0.14
    éħ
    0.14
    eração
    0.14
    оÑıн
    0.14
    ãĥĥãĥĹ
    0.13
    flater
    0.13
    Act Density 0.155%

    No Known Activations