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

    Neuronpedia

    INDEX
    Explanations

    contractions such as "here's" or "it's"

    oai_token-act-pair · gpt-3.5-turbo

    phrases introducing or referencing a JSON file or data structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aneers
    -0.71
    hate
    -0.67
    ange
    -0.67
    sed
    -0.67
    esm
    -0.67
    alties
    -0.67
    existent
    -0.64
    stocks
    -0.64
    icc
    -0.64
    cult
    -0.64
    POSITIVE LOGITS
     hoping
    0.84
     another
    0.73
     excerpt
    0.72
    :(
    0.70
     rundown
    0.69
     Shooter
    0.68
     Haf
    0.68
    :-
    0.68
     why
    0.67
     Darrell
    0.66
    Act Density 0.049%

    No Known Activations