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

    Neuronpedia

    INDEX
    Explanations

    names of individuals or proper nouns in the context of significant actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    selection
    -0.69
     manipulating
    -0.65
     '.
    -0.64
     disproportion
    -0.63
     interfering
    -0.62
    LEASE
    -0.61
    âĶĢâĶĢ
    -0.61
     preferential
    -0.60
    paralle
    -0.60
     %%
    -0.60
    POSITIVE LOGITS
     said
    1.14
    Said
    1.00
     exclaimed
    0.97
     wrote
    0.96
     says
    0.94
     told
    0.93
     joked
    0.92
     recalls
    0.92
    said
    0.90
     recalled
    0.89
    Act Density 0.104%

    No Known Activations