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

    Neuronpedia

    INDEX
    Explanations

    instances where something is being established or arranged

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the act of establishing or initiating something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obi
    -0.77
    oh
    -0.68
    onso
    -0.68
    annah
    -0.67
    uma
    -0.66
    catentry
    -0.65
    Brow
    -0.65
    hound
    -0.65
    axe
    -0.64
    GA
    -0.59
    POSITIVE LOGITS
     tents
    0.88
     shop
    0.87
     camp
    0.78
    olicy
    0.72
     tenancy
    0.72
     toilets
    0.69
     partitions
    0.69
     turrets
    0.69
     rapport
    0.68
    dule
    0.67
    Act Density 0.033%

    No Known Activations