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

    Neuronpedia

    INDEX
    Explanations

    instances of emphasis or importance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "even."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rend
    -0.88
    aim
    -0.82
    hammad
    -0.72
    Exit
    -0.71
    unity
    -0.71
    scribe
    -0.70
    cel
    -0.68
    aye
    -0.68
    asy
    -0.66
    main
    -0.66
    POSITIVE LOGITS
     remotely
    0.93
     though
    0.91
     tho
    0.90
    handedly
    0.89
     joked
    0.78
     hinted
    0.76
    handed
    0.75
     briefly
    0.74
     managed
    0.72
     entertained
    0.70
    Act Density 0.056%

    No Known Activations