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

    Neuronpedia

    INDEX
    Explanations

    references to leadership roles and their associated titles

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

    job, Jonah

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     institute
    -0.33
     affiliated
    -0.32
    aarrggbb
    -0.32
     mümkün
    -0.32
     institución
    -0.30
     incin
    -0.30
    expires
    -0.30
    +#+
    -0.30
     тамо
    -0.29
     institution
    -0.29
    POSITIVE LOGITS
     Job
    1.64
    Job
    1.50
     JOB
    1.05
    JOB
    0.98
     Jobs
    0.84
     Jonah
    0.84
    Jonah
    0.80
    getJob
    0.74
     jobber
    0.72
    IntoConstraints
    0.69
    Act Density 0.007%

    No Known Activations