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

    Neuronpedia

    INDEX
    Explanations

    combinations of words related to specific occupations or employment-related contexts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    peak
    -0.66
    plings
    -0.64
    disc
    -0.64
    rams
    -0.60
    zac
    -0.60
    translation
    -0.60
    pack
    -0.60
    ectar
    -0.59
    asio
    -0.59
    cong
    -0.59
    POSITIVE LOGITS
    ALLY
    0.73
    ally
    0.71
    ATTLE
    0.66
     Occupations
    0.65
    als
    0.64
    ational
    0.64
    forces
    0.64
     occupation
    0.63
    eering
    0.62
     force
    0.62
    Act Density 6.134%

    No Known Activations