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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Phillips."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ERAL
    -0.84
     quo
    -0.75
    gary
    -0.73
    clud
    -0.73
    hibition
    -0.72
    joined
    -0.72
    izen
    -0.71
    ctors
    -0.71
    flow
    -0.70
    worthiness
    -0.68
    POSITIVE LOGITS
    ippi
    0.89
     Phillips
    0.86
    pie
    0.85
     Parsons
    0.85
    ipher
    0.79
    sey
    0.78
    ussen
    0.76
     Lovecraft
    0.74
    burgh
    0.74
     nails
    0.72
    Act Density 0.009%

    No Known Activations