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

    Neuronpedia

    INDEX
    Explanations

    interesting statements or topics

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating something is noteworthy or engaging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otent
    -0.74
    arest
    -0.71
    reditation
    -0.71
    oise
    -0.70
    uts
    -0.69
    avers
    -0.69
    required
    -0.68
    uter
    -0.68
    sorry
    -0.67
    ussy
    -0.67
    POSITIVE LOGITS
     tid
    0.95
     trivia
    0.93
     anecdotes
    0.90
     juxtap
    0.89
     twists
    0.87
    arios
    0.85
     Flavoring
    0.83
     disse
    0.83
     insights
    0.82
     discoveries
    0.81
    Act Density 0.064%

    No Known Activations