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

    Neuronpedia

    INDEX
    Explanations

    constructs that initiate statements or questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kuk
    -0.16
    inyin
    -0.15
    cela
    -0.15
    ContentLoaded
    -0.15
    apesh
    -0.14
    mania
    -0.14
    endir
    -0.14
    stable
    -0.14
    stå
    -0.14
    ogany
    -0.14
    POSITIVE LOGITS
     far
    0.20
    far
    0.17
    ief
    0.15
    IVA
    0.15
    ething
    0.15
    yl
    0.15
    oner
    0.15
    iled
    0.15
    _far
    0.15
    GES
    0.14
    Act Density 0.072%

    No Known Activations