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

    Neuronpedia

    INDEX
    Explanations

    discussion of military tactics and historical battles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acro
    -0.15
    zcze
    -0.15
    alem
    -0.15
    umas
    -0.14
    chein
    -0.14
    ecture
    -0.13
    ecta
    -0.13
    errick
    -0.13
    lei
    -0.13
    stash
    -0.13
    POSITIVE LOGITS
     mus
    0.28
     cu
    0.26
     Horse
    0.26
     foot
    0.26
     horse
    0.26
     Foot
    0.25
     pik
    0.25
     cav
    0.25
     Musk
    0.24
     mounted
    0.23
    Act Density 0.050%

    No Known Activations