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

    Neuronpedia

    INDEX
    Explanations

    positive evaluations of performance or effort

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

    Preceding possessive pronouns or "amazing"

    np_acts-logits-general · gemini-2.0-flash

    doing a job

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.58
     ویکی‌آمباردا
    -0.56
     HasFactory
    -0.54
     Empieza
    -0.53
    Opportunity
    -0.52
    MENAFN
    -0.51
    autique
    -0.51
    licability
    -0.50
    Opportunities
    -0.49
    Tembelea
    -0.49
    POSITIVE LOGITS
     job
    1.68
    job
    1.41
     Job
    1.23
    Job
    1.23
     JOB
    1.18
    JOB
    1.07
     jobs
    1.03
     jobb
    0.93
    jobs
    0.86
     deed
    0.81
    Act Density 0.119%

    No Known Activations