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

    Neuronpedia

    INDEX
    Explanations

    words related to views, perspectives, beliefs, and thoughts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ammy
    -0.64
    ciating
    -0.60
    glomer
    -0.60
    Interstitial
    -0.59
    isol
    -0.59
     earthqu
    -0.58
    Lex
    -0.58
    ilant
    -0.58
    arser
    -0.58
     Explos
    -0.57
    POSITIVE LOGITS
    finder
    0.99
     views
    0.83
    ports
    0.81
    opian
    0.73
     view
    0.72
    points
    0.71
    topic
    0.70
     viewpoint
    0.69
    port
    0.69
    ership
    0.68
    Act Density 8.715%

    No Known Activations