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

    Neuronpedia

    INDEX
    Explanations

    details about incidents or events related to security threats and national security

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    èª
    -0.74
    hedon
    -0.67
    tone
    -0.65
    ube
    -0.64
    Phys
    -0.63
    ¯
    -0.63
    igraph
    -0.61
     Prometheus
    -0.60
    £
    -0.60
    Sax
    -0.59
    POSITIVE LOGITS
     counting
    1.09
     totaling
    1.02
     assorted
    0.98
     six
    0.92
     dozens
    0.91
     thirteen
    0.90
     eleven
    0.88
     fourteen
    0.87
     seven
    0.86
     countless
    0.86
    Act Density 0.261%

    No Known Activations