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

    Neuronpedia

    INDEX
    Explanations

    phrases related to collaboration and working together

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    icter
    -0.79
    endar
    -0.79
    apest
    -0.78
    aught
    -0.77
    lav
    -0.77
    alid
    -0.74
    yll
    -0.73
    SPONSORED
    -0.70
    aughtered
    -0.70
    ova
    -0.70
    POSITIVE LOGITS
     unsuspecting
    0.88
     weeds
    0.87
     temptation
    0.80
     booze
    0.80
     pesky
    0.79
     shenanigans
    0.77
     bandwagon
    0.77
     negativity
    0.72
     corners
    0.71
     whining
    0.70
    Act Density 0.661%

    No Known Activations