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

    Neuronpedia

    INDEX
    Explanations

    references to public speaking events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "speech" and related contexts about delivering speeches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Soldiers
    -0.65
    involved
    -0.63
    âĺħ
    -0.60
     saline
    -0.60
    rome
    -0.59
     Associ
    -0.57
     Coast
    -0.56
     Mississ
    -0.56
     Construct
    -0.55
    olved
    -0.54
    POSITIVE LOGITS
    writers
    0.99
    writer
    0.98
     speeches
    0.89
     speech
    0.86
    speech
    0.86
    orial
    0.83
    writing
    0.83
    boxing
    0.77
     Speech
    0.76
     delivered
    0.74
    Act Density 0.048%

    No Known Activations