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

    Neuronpedia

    INDEX
    Explanations

    instances of the article "a" as well as certain prepositions and noun phrases related to counting and anaphoric expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     entry
    -0.71
     McDonnell
    -0.62
    sylvania
    -0.60
    rolet
    -0.60
    icz
    -0.58
    orius
    -0.58
    tymology
    -0.56
     Advanced
    -0.54
    omas
    -0.54
     appell
    -0.53
    POSITIVE LOGITS
     sudden
    1.11
    purpose
    0.70
     goddamn
    0.66
     freaking
    0.62
     stripe
    0.60
     fury
    0.57
    ooo
    0.56
     goodness
    0.56
    oots
    0.55
    FFFF
    0.55
    Act Density 0.021%

    No Known Activations