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

    Neuronpedia

    INDEX
    Explanations

    words related to names and titles of individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly the name "Abe."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igans
    -0.73
     Cassidy
    -0.66
    LINE
    -0.64
    otle
    -0.62
    ivity
    -0.62
    oner
    -0.60
    aldehyde
    -0.60
     Telephone
    -0.60
     Xie
    -0.60
     vans
    -0.58
    POSITIVE LOGITS
    ment
    0.84
    llor
    0.82
    ful
    0.81
    tered
    0.81
    untarily
    0.78
    cy
    0.78
    inel
    0.78
    tle
    0.74
    uer
    0.74
    ures
    0.74
    Act Density 0.043%

    No Known Activations