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

    Neuronpedia

    INDEX
    Explanations

    terms related to military tactics and locations present in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to locations or positions of military or strategic significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    spection
    -0.73
     Parks
    -0.64
    qualified
    -0.63
    trans
    -0.63
    Artist
    -0.61
    ptin
    -0.61
    itting
    -0.60
     Einstein
    -0.60
     Schr
    -0.59
    IRC
    -0.59
    POSITIVE LOGITS
     stronghold
    3.42
     strongh
    3.01
     bast
    2.10
     foothold
    1.96
    rongh
    1.67
     Stronghold
    1.62
     Strongh
    1.53
     battleground
    1.40
     fortress
    1.34
     footh
    1.32
    Act Density 0.012%

    No Known Activations