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

    Neuronpedia

    INDEX
    Explanations

    references to colonies and related terms, such as colony, colonies, colonists, and manager

    oai_token-act-pair · gpt-3.5-turbo

    references to colonies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ya
    -0.82
     FANTASY
    -0.79
    Downloadha
    -0.79
    angers
    -0.78
    ostic
    -0.76
    inen
    -0.75
     partName
    -0.75
    amac
    -0.74
    aciously
    -0.72
    andro
    -0.72
    POSITIVE LOGITS
     Colony
    0.86
     colony
    0.84
     colonies
    0.81
    eers
    0.77
     outpost
    0.76
     pigeon
    0.74
     abroad
    0.72
    mates
    0.71
     Colon
    0.69
     ship
    0.65
    Act Density 0.035%

    No Known Activations