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

    Neuronpedia

    INDEX
    Explanations

    common conjunctions and prepositions indicating relationships between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iesel
    -0.18
    addock
    -0.17
     Kee
    -0.17
    Äįin
    -0.16
     Gin
    -0.15
    даÑħ
    -0.14
    _clr
    -0.14
    icie
    -0.14
     |_|
    -0.14
    480
    -0.14
    POSITIVE LOGITS
     Guar
    0.15
     Guard
    0.15
    leÅŁik
    0.14
    /front
    0.14
    \-
    0.14
    殿
    0.14
    lying
    0.14
    iec
    0.14
    ãĥ¼ãĥ
    0.13
     discre
    0.13
    Act Density 0.002%

    No Known Activations