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

    Neuronpedia

    INDEX
    Explanations

    phrases or words that make something exceptional or distinct

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    elf
    -0.84
     conn
    -0.66
     lockout
    -0.65
     PRESIDENT
    -0.63
    ynthesis
    -0.62
     confir
    -0.62
     typo
    -0.60
    ãĥį
    -0.60
     contracted
    -0.60
    uthor
    -0.60
    POSITIVE LOGITS
     prominently
    0.87
     amongst
    0.87
    ingly
    0.83
     brightly
    0.80
     among
    0.79
     Flavoring
    0.78
     aest
    0.75
     visually
    0.75
    ocl
    0.75
    Recommend
    0.75
    Act Density 0.200%

    No Known Activations