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

    Neuronpedia

    INDEX
    Explanations

    discourse markers and transitions in a dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    luž
    -0.18
    eyen
    -0.15
    CellStyle
    -0.15
    ãģĮãģĬ
    -0.14
    WithDuration
    -0.14
    äng
    -0.14
    OrFail
    -0.14
    ãģªãģıãģª
    -0.14
    lá
    -0.13
    ondo
    -0.13
    POSITIVE LOGITS
     let
    0.56
     lets
    0.45
     allow
    0.43
    let
    0.43
     Let
    0.40
     Allow
    0.39
    Let
    0.36
    	let
    0.36
     here
    0.36
     permit
    0.36
    Act Density 0.195%

    No Known Activations