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

    Neuronpedia

    INDEX
    Explanations

    prepositions and conjunctions indicating relationships or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cos
    -0.15
    ãĥ¼ãĥ¬
    -0.15
     Demp
    -0.15
    heimer
    -0.14
    odore
    -0.14
     ((__
    -0.14
    itere
    -0.14
    liÄį
    -0.13
    East
    -0.13
    orio
    -0.13
    POSITIVE LOGITS
    ãĥ³ãĤ¿
    0.16
    onta
    0.15
     Strap
    0.15
    ATAR
    0.15
    echa
    0.14
    ikip
    0.14
     Zhu
    0.14
    _ALT
    0.14
    INCT
    0.14
    ntax
    0.14
    Act Density 0.016%

    No Known Activations