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

    Neuronpedia

    INDEX
    Explanations

    situations involving wrongdoing, investigations, and financial penalties

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     sunset
    -0.86
     sneak
    -0.83
     reception
    -0.81
     grounding
    -0.78
     marked
    -0.78
     discrete
    -0.75
     tide
    -0.74
     choke
    -0.74
     induct
    -0.73
     portrait
    -0.72
    POSITIVE LOGITS
    com
    1.78
    org
    1.76
    exe
    1.54
    net
    1.47
    Org
    1.42
    blogspot
    1.39
    wordpress
    1.38
    gov
    1.36
    info
    1.35
    edu
    1.34
    Act Density 0.218%

    No Known Activations