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

    Neuronpedia

    INDEX
    Explanations

    comments or references to commenting within text

    oai_token-act-pair · gpt-3.5-turbo

    instances of comments and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pocket
    -0.74
     Lans
    -0.69
     Recon
    -0.68
     Sinai
    -0.68
    fold
    -0.68
    Sensor
    -0.67
    ccording
    -0.65
    nown
    -0.64
     turf
    -0.64
    ãĥ¼ãĥ«
    -0.64
    POSITIVE LOGITS
    ariat
    1.00
    ature
    0.94
    atively
    0.91
    atures
    0.87
    aries
    0.84
     comments
    0.80
     comment
    0.78
    ators
    0.76
    comments
    0.75
    aires
    0.73
    Act Density 0.034%

    No Known Activations