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

    Neuronpedia

    INDEX
    Explanations

    celebrity names and mentions

    oai_token-act-pair · gpt-3.5-turbo

    prominent names or individuals associated with a particular context or topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ources
    -0.70
    olars
    -0.69
     realise
    -0.66
     doub
    -0.66
    ictional
    -0.66
     ditch
    -0.64
     fortunate
    -0.63
    rentices
    -0.63
    iners
    -0.62
     redes
    -0.62
    POSITIVE LOGITS
     etc
    1.27
    etc
    1.19
    ĪĴ
    0.87
     Jr
    0.77
     Aqu
    0.76
     Sea
    0.74
    76561
    0.73
     Sof
    0.72
    Org
    0.69
     RTX
    0.69
    Act Density 0.257%

    No Known Activations