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

    Neuronpedia

    INDEX
    Explanations

    numerical values and references to groups of people involved in significant historical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     populations
    -0.19
     billions
    -0.18
     fleets
    -0.17
     millions
    -0.17
    .groups
    -0.16
     crews
    -0.16
     Millions
    -0.16
     Groups
    -0.16
    illions
    -0.16
     groups
    -0.16
    POSITIVE LOGITS
     men
    0.18
     uniform
    0.18
    -mask
    0.17
    masked
    0.17
     masked
    0.17
     gathered
    0.16
    emen
    0.16
     Ñĩеловек
    0.16
    -member
    0.15
     unidentified
    0.15
    Act Density 0.120%

    No Known Activations