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

    Neuronpedia

    INDEX
    Explanations

    dates written in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    dates and numerical values indicating time or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     parap
    -0.70
     pregn
    -0.67
     strugg
    -0.65
     indisp
    -0.63
     fortun
    -0.63
     unaccount
    -0.61
     dwar
    -0.60
     spo
    -0.59
    accompanied
    -0.59
     deserving
    -0.58
    POSITIVE LOGITS
     Tweet
    0.79
     Invalid
    0.78
     [+]
    0.73
    rils
    0.70
    Invalid
    0.68
    raint
    0.67
    poons
    0.66
    amation
    0.65
     09
    0.65
    iatus
    0.65
    Act Density 0.066%

    No Known Activations