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

    Neuronpedia

    INDEX
    Explanations

    words related to roles and positions within organizations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    nings
    -0.83
    jad
    -0.74
     plans
    -0.74
    venants
    -0.72
    ples
    -0.70
    iland
    -0.67
    breaks
    -0.66
     samples
    -0.66
    projects
    -0.65
    Flow
    -0.63
    POSITIVE LOGITS
     overseeing
    0.91
     medi
    0.88
     holder
    0.82
     overse
    0.81
     educating
    0.79
     defending
    0.78
     protector
    0.77
     protecting
    0.77
     lookout
    0.76
     guardian
    0.76
    Act Density 0.298%

    No Known Activations