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

    Neuronpedia

    INDEX
    Explanations

    specific instances where the word "this" is referenced

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "this" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ometown
    -0.78
    Ĭ±
    -0.76
    arson
    -0.76
    erity
    -0.69
    politics
    -0.69
    Ùħ
    -0.67
    doms
    -0.65
     Phelps
    -0.65
    lev
    -0.62
    fred
    -0.62
    POSITIVE LOGITS
     item
    1.15
     trope
    1.14
     wiki
    1.08
     section
    1.06
     method
    1.05
     guide
    1.04
     addon
    1.03
     technique
    1.00
     tutorial
    0.95
     trait
    0.95
    Act Density 0.159%

    No Known Activations