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

    Neuronpedia

    INDEX
    Explanations

    strings of numbers

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to locations and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     conduc
    -0.88
     behav
    -0.79
    soDeliveryDate
    -0.73
    blance
    -0.67
    Connector
    -0.66
     shenan
    -0.65
     explan
    -0.64
     traged
    -0.63
    é»Ĵ
    -0.63
     showc
    -0.62
    POSITIVE LOGITS
    olin
    0.63
    amina
    0.62
     Fernand
    0.61
    anton
    0.59
    atin
    0.57
     389
    0.57
    farm
    0.56
    age
    0.55
    uns
    0.55
    arters
    0.55
    Act Density 0.205%

    No Known Activations