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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific locations or roles within an organization

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with positions or roles in organizations and competitive contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anson
    -0.51
    lif
    -0.51
    cern
    -0.50
    vae
    -0.50
    psc
    -0.50
    wic
    -0.50
    ļé
    -0.50
    NetMessage
    -0.49
    ewitness
    -0.49
    userc
    -0.48
    POSITIVE LOGITS
     aisle
    0.66
    iest
    0.65
     throne
    0.59
     fraternity
    0.57
    forts
    0.57
    liest
    0.57
    eers
    0.56
     IPM
    0.56
     portion
    0.56
    finals
    0.54
    Act Density 0.465%

    No Known Activations