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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and connecting phrases that indicate complex sentence structures or relations between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etimes
    -0.16
    práv
    -0.15
    eldom
    -0.14
    .gg
    -0.14
     âĹĦ
    -0.14
     outcry
    -0.13
    handled
    -0.13
     بداÙĨ
    -0.13
    MX
    -0.13
    uzzi
    -0.13
    POSITIVE LOGITS
     added
    0.27
     suggested
    0.22
     said
    0.22
     pointed
    0.21
     noted
    0.21
    Added
    0.21
     that
    0.20
    added
    0.19
     Added
    0.19
    warn
    0.19
    Act Density 0.126%

    No Known Activations