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

    Neuronpedia

    INDEX
    Explanations

    verbs related to leaving or departing

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "left" indicating departures or exits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wcsstore
    -0.94
    alist
    -0.78
    MAT
    -0.71
     Cosponsors
    -0.68
    rg
    -0.67
    intend
    -0.66
    hest
    -0.64
    MpServer
    -0.63
    oys
    -0.62
    Percent
    -0.62
    POSITIVE LOGITS
     undone
    0.98
    overs
    0.96
     behind
    0.83
     unexpl
    0.78
    wich
    0.76
     overboard
    0.75
     untreated
    0.74
     Aleppo
    0.71
     town
    0.71
     Behind
    0.70
    Act Density 0.053%

    No Known Activations