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

    Neuronpedia

    INDEX
    Explanations

    specific nouns and phrases related to preferences or choices

    oai_token-act-pair · gpt-3.5-turbo

    references to behavior and choices affecting individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,—
    -0.84
    alysed
    -0.73
    oeuv
    -0.72
    operation
    -0.72
    :-
    -0.71
    £
    -0.69
    fax
    -0.67
    `.
    -0.67
    .(
    -0.66
    âĢ¦âĢ¦âĢ¦âĢ¦
    -0.65
    POSITIVE LOGITS
     Philly
    0.79
     Millennials
    0.75
     moms
    0.72
     Nerd
    0.71
     millennials
    0.71
     NFL
    0.69
     Lyft
    0.69
     Yelp
    0.67
     Seahawks
    0.66
     Nashville
    0.66
    Act Density 1.824%

    No Known Activations