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

    Neuronpedia

    INDEX
    Explanations

    text relating to authorship and citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ustom
    -0.18
    ÙĦÙĪد
    -0.17
    trand
    -0.15
    $core
    -0.14
     conven
    -0.14
     Harlem
    -0.14
    rade
    -0.13
    uffs
    -0.13
     Headquarters
    -0.13
    &id
    -0.13
    POSITIVE LOGITS
    idor
    0.17
    alth
    0.15
    inden
    0.15
    RouterModule
    0.15
    bor
    0.13
    itler
    0.13
    úb
    0.13
     OT
    0.13
     Mang
    0.13
    èı
    0.13
    Act Density 0.081%

    No Known Activations