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

    Neuronpedia

    INDEX
    Explanations

    posts or articles on social media

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    tics
    -0.83
    itudes
    -0.73
    ses
    -0.72
    ernels
    -0.69
     Occupations
    -0.63
    ospels
    -0.62
    urches
    -0.62
     establishments
    -0.62
     virtues
    -0.61
    NetMessage
    -0.60
    POSITIVE LOGITS
     Called
    0.74
     titled
    0.72
     called
    0.70
    less
    0.70
    atical
    0.70
     resembling
    0.69
    called
    0.69
    usually
    0.69
     reminiscent
    0.69
    alyst
    0.68
    Act Density 0.390%

    No Known Activations