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

    Neuronpedia

    INDEX
    Explanations

    phrases related to geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns associated with geographical locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avin
    -0.75
    ampton
    -0.73
    Adams
    -0.68
    utherford
    -0.67
     Tucker
    -0.66
    OULD
    -0.65
    prints
    -0.64
    âĿ
    -0.63
     Sahara
    -0.62
    Afee
    -0.61
    POSITIVE LOGITS
    dayName
    0.75
    ulner
    0.72
    Engineers
    0.66
     surge
    0.62
    irl
    0.61
     governing
    0.60
    omorph
    0.60
     harb
    0.59
    gap
    0.59
     underlying
    0.58
    Act Density 0.000%

    No Known Activations