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

    Neuronpedia

    INDEX
    Explanations

    names of job roles or positions within organizations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     oneself
    -0.68
     Purg
    -0.67
    algia
    -0.65
    rosso
    -0.62
    Spawn
    -0.61
     yourselves
    -0.60
    nice
    -0.60
    enstein
    -0.60
     Federation
    -0.60
    à¥
    -0.59
    POSITIVE LOGITS
     overseeing
    0.82
    mate
    0.81
    mates
    0.81
     mate
    0.76
    abilities
    0.74
     mates
    0.74
    span
    0.72
    ional
    0.71
    manship
    0.68
    holding
    0.68
    Act Density 0.121%

    No Known Activations