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

    Neuronpedia

    INDEX
    Explanations

    terms related to stability and structural integrity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     squ
    -0.15
    709
    -0.14
    Æ°
    -0.14
     Ekon
    -0.14
    phis
    -0.14
    yes
    -0.14
    inite
    -0.13
    lean
    -0.13
     Lit
    -0.13
     Opr
    -0.13
    POSITIVE LOGITS
     throughout
    0.17
    angelo
    0.15
     Stay
    0.15
     stay
    0.15
    -scrollbar
    0.15
     ìľłì§Ģ
    0.14
    аза
    0.14
     balance
    0.14
     sharp
    0.14
    stav
    0.14
    Act Density 0.104%

    No Known Activations