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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "more" in various contexts, indicating a focus on comparison and enhancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flo
    -0.17
    ox
    -0.16
     Flood
    -0.16
    (
    -0.16
    iden
    -0.15
     bro
    -0.15
     Marie
    -0.15
     (
    -0.15
    iche
    -0.14
    atri
    -0.14
    POSITIVE LOGITS
    istrat
    0.16
    άκ
    0.16
     neod
    0.15
     Unidos
    0.15
    chluss
    0.15
    Sizer
    0.15
    -direct
    0.15
    racak
    0.15
    emente
    0.14
    mts
    0.14
    Act Density 0.116%

    No Known Activations