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

    Neuronpedia

    INDEX
    Explanations

    phrases related to writing or content creation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pedia
    -0.19
    imir
    -0.15
    ubo
    -0.15
    .ng
    -0.14
    anic
    -0.14
    erno
    -0.14
    ours
    -0.14
     chiá»ģu
    -0.14
    etto
    -0.14
     Metallic
    -0.14
    POSITIVE LOGITS
     Inner
    0.17
    artz
    0.16
    abble
    0.16
     Mori
    0.16
    el
    0.15
     Merlin
    0.15
    atl
    0.15
    >Main
    0.14
    _fatal
    0.14
    nce
    0.13
    Act Density 0.152%

    No Known Activations