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

    Neuronpedia

    INDEX
    Explanations

    people or entities that are "in charge of" something

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases related to being in charge or responsible

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     partName
    -0.69
    dayName
    -0.69
    venants
    -0.66
    olith
    -0.63
    nets
    -0.62
    enth
    -0.62
    prises
    -0.62
    soType
    -0.61
     deserts
    -0.61
     compromises
    -0.60
    POSITIVE LOGITS
    thood
    0.74
    riage
    0.72
    lain
    0.70
    orney
    0.70
     overseeing
    0.70
    eering
    0.68
     maintaining
    0.66
     Badge
    0.64
     perjury
    0.64
    ãģĤ
    0.64
    Act Density 0.077%

    No Known Activations