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

    Neuronpedia

    INDEX
    Explanations

    requests for help or assistance

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    rug
    -0.84
    onga
    -0.76
     Cosponsors
    -0.70
    ander
    -0.70
    ogi
    -0.69
     âĸº
    -0.69
    PsyNetMessage
    -0.68
    wark
    -0.68
    RIC
    -0.68
    ocol
    -0.67
    POSITIVE LOGITS
     again
    1.05
     Upon
    0.92
     bitten
    0.89
     upon
    0.77
     mastered
    0.75
     reunited
    0.74
     tasted
    0.74
     seated
    0.73
    again
    0.70
     satisfied
    0.70
    Act Density 0.325%

    No Known Activations