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

    Neuronpedia

    INDEX
    Explanations

    mentions of careers and job-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    careers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sandstone
    -0.48
     mid
    -0.46
     Olsson
    -0.44
     Middleton
    -0.44
     Lob
    -0.44
     rooftops
    -0.43
    Solid
    -0.43
     Junta
    -0.42
     Highlights
    -0.42
    <bos>
    -0.42
    POSITIVE LOGITS
     careers
    1.30
     Careers
    1.13
    careers
    1.09
    Careers
    1.06
     carreras
    0.57
     carreira
    0.56
     configureStore
    0.55
     Meksiku
    0.55
    Carreira
    0.54
    ьажоргаш
    0.53
    Act Density 0.004%

    No Known Activations