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

    Neuronpedia

    INDEX
    Explanations

    words related to environmental issues and political events

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    cakes
    -0.68
    ahs
    -0.67
    usercontent
    -0.62
     Tracks
    -0.62
     Mas
    -0.61
    Pros
    -0.60
    isms
    -0.59
     Saud
    -0.59
    Son
    -0.59
    mans
    -0.59
    POSITIVE LOGITS
     scenario
    0.81
     influx
    0.80
     newfound
    0.80
     regard
    0.73
     circumstance
    0.72
     latter
    0.70
     reasoning
    0.70
    ilege
    0.70
     complication
    0.69
     equation
    0.68
    Act Density 7.414%

    No Known Activations