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

    Neuronpedia

    INDEX
    Explanations

    expressions or descriptions indicating something is simplistic or lacking in complexity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     brows
    -0.15
    atre
    -0.14
    aclass
    -0.14
    uling
    -0.14
     blind
    -0.14
    byss
    -0.14
    chef
    -0.14
     Bib
    -0.14
    mania
    -0.14
    ën
    -0.13
    POSITIVE LOGITS
    ings
    0.19
    ãĢħ
    0.17
    /plain
    0.17
    IDER
    0.16
    é¾
    0.16
    clo
    0.16
    миÑĤ
    0.16
    -ÑĤаки
    0.16
    chant
    0.15
     à¹Ĩ
    0.15
    Act Density 0.008%

    No Known Activations