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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "it" or "things."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fare
    -0.17
    âr
    -0.14
    reinterpret
    -0.14
    ategy
    -0.14
    .scalablytyped
    -0.14
    _ie
    -0.13
    apers
    -0.13
    uard
    -0.13
    gies
    -0.13
    fuse
    -0.13
    POSITIVE LOGITS
     Christoph
    0.16
    acula
    0.16
    .emf
    0.15
    ìĿµ
    0.15
     Schul
    0.14
     Cant
    0.14
    amura
    0.14
    ideo
    0.14
    ags
    0.14
    ê·¹
    0.14
    Act Density 0.037%

    No Known Activations