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

    Neuronpedia

    INDEX
    Explanations

    names of individuals or specific persons

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĹ¼
    -0.81
    channelAvailability
    -0.72
     aisle
    -0.68
    è¯
    -0.67
     checkout
    -0.66
    shapeshifter
    -0.64
     CTR
    -0.63
     sidx
    -0.63
     [|
    -0.63
     explanatory
    -0.62
    POSITIVE LOGITS
     Nguyen
    0.73
    Nap
    0.73
    leen
    0.71
    jo
    0.69
    Anne
    0.68
    nil
    0.68
     Ni
    0.68
     Gerard
    0.67
     Wong
    0.67
    lan
    0.67
    Act Density 0.342%

    No Known Activations