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

    Neuronpedia

    INDEX
    Explanations

    names of people separated by commas

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     footing
    -0.75
    ources
    -0.72
    around
    -0.65
    bert
    -0.64
    ocial
    -0.63
    ight
    -0.63
    "!
    -0.63
     guiActiveUn
    -0.63
     therap
    -0.61
    natureconservancy
    -0.61
    POSITIVE LOGITS
     etc
    1.31
    etc
    1.07
    ĪĴ
    0.74
    Org
    0.74
    76561
    0.72
     Guan
    0.71
    ioch
    0.71
     Mehran
    0.68
     Kinnikuman
    0.68
     Sof
    0.67
    Act Density 0.265%

    No Known Activations