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

    Neuronpedia

    INDEX
    Explanations

    mentions of Mars and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eten
    -0.23
    lass
    -0.17
    ogue
    -0.17
    ointed
    -0.16
    atched
    -0.16
    orra
    -0.16
    thers
    -0.15
    agem
    -0.15
    ortal
    -0.15
    ivers
    -0.15
    POSITIVE LOGITS
    den
    0.29
    upil
    0.24
    dens
    0.21
    ilio
    0.20
     Attacks
    0.18
    iglia
    0.18
    yas
    0.18
    illac
    0.18
     rover
    0.17
     Rover
    0.17
    Act Density 0.010%

    No Known Activations