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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the term "Cons" or variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WOOD
    -0.77
     Meadow
    -0.71
     Hoover
    -0.68
     Ames
    -0.66
     Amos
    -0.66
     scratch
    -0.65
     Afghans
    -0.64
    ILLE
    -0.64
     Gamb
    -0.64
     Wast
    -0.63
    POSITIVE LOGITS
    ervatives
    1.50
    umers
    1.49
    idered
    1.49
    ensus
    1.47
    piracy
    1.46
    ensual
    1.43
    cientious
    1.39
    istent
    1.38
    olid
    1.33
    umed
    1.31
    Act Density 0.025%

    No Known Activations