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

    Neuronpedia

    INDEX
    Explanations

    statements providing explanations or descriptions of concepts or observations

    oai_token-act-pair · gpt-3.5-turbo

    scholarly assertions and citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SHARE
    -0.69
    wives
    -0.64
     condol
    -0.64
    Cele
    -0.61
    fired
    -0.59
    ranged
    -0.58
    luck
    -0.58
     clicked
    -0.58
    naissance
    -0.58
    thumbnails
    -0.57
    POSITIVE LOGITS
     convinc
    0.94
     extensively
    0.85
     empir
    0.82
     rhet
    0.81
     quotes
    0.81
     "âĢ¦
    0.81
     anecdotes
    0.78
     explicitly
    0.77
     quoting
    0.76
     "...
    0.75
    Act Density 0.303%

    No Known Activations