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

    Neuronpedia

    INDEX
    Explanations

    specific phrases or structures related to discussions of capability and possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñĥз
    -0.15
    bove
    -0.15
    ouri
    -0.15
    λιά
    -0.15
    OND
    -0.15
    _firestore
    -0.14
    _skin
    -0.14
    panion
    -0.13
    izu
    -0.13
    /documentation
    -0.13
    POSITIVE LOGITS
     en
    0.15
    qli
    0.15
     nowhere
    0.14
     Freak
    0.14
    kest
    0.13
    lse
    0.13
     Ih
    0.13
    ender
    0.13
     end
    0.13
     gef
    0.13
    Act Density 0.537%

    No Known Activations