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

    Neuronpedia

    INDEX
    Explanations

    information related to annual financial amounts or wages

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'a' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hess
    -0.78
    ELL
    -0.75
    Edit
    -0.72
    tal
    -0.69
    ADRA
    -0.69
    :[
    -0.69
    NK
    -0.68
    forth
    -0.66
    baugh
    -0.66
     Ern
    -0.64
    POSITIVE LOGITS
     month
    1.04
     decade
    0.97
     week
    0.95
     year
    0.94
     pound
    0.91
     quarter
    0.88
     person
    0.88
     capita
    0.87
    rouse
    0.86
     lot
    0.85
    Act Density 0.057%

    No Known Activations