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

    Neuronpedia

    INDEX
    Explanations

    mentions of names, particularly "Wade" or "Deadpool."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Wade."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogy
    -0.79
    rador
    -0.79
    undai
    -0.77
    atem
    -0.74
    aucus
    -0.74
    ffic
    -0.73
    inance
    -0.73
    inates
    -0.73
    ccording
    -0.71
    phis
    -0.71
    POSITIVE LOGITS
     Wade
    1.18
     Bauer
    0.90
     Phillips
    0.86
     Bosh
    0.84
    nesday
    0.82
     Hole
    0.82
     Jarvis
    0.82
     Chandler
    0.77
     Dixon
    0.76
     Davis
    0.76
    Act Density 0.007%

    No Known Activations