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

    Neuronpedia

    INDEX
    Explanations

    proper nouns of surnames

    oai_token-act-pair · gpt-3.5-turbo

    the name "Phillips" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ERAL
    -0.87
     quo
    -0.77
    hibition
    -0.76
    ctors
    -0.75
    gary
    -0.74
    fy
    -0.72
    clud
    -0.69
    joined
    -0.69
    gha
    -0.66
    think
    -0.66
    POSITIVE LOGITS
    ippi
    0.96
     Lovecraft
    0.84
    pie
    0.77
    sey
    0.77
    burgh
    0.76
     Parsons
    0.73
    ussen
    0.73
    atile
    0.72
     Phillips
    0.71
    ipher
    0.70
    Act Density 0.017%

    No Known Activations