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

    Neuronpedia

    INDEX
    Explanations

    actions related to human behaviors and activities

    oai_token-act-pair · gpt-3.5-turbo

    actions related to consumption and ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     millenn
    -0.69
     Gunn
    -0.66
     Kle
    -0.61
     Pere
    -0.58
     Vul
    -0.58
     coercive
    -0.57
     Shu
    -0.57
     Ballard
    -0.56
     Bere
    -0.56
     Yel
    -0.56
    POSITIVE LOGITS
    */(
    0.77
    abouts
    0.74
    .'
    0.73
     WITHOUT
    0.71
     ('
    0.69
    .:
    0.69
     beforehand
    0.67
    .</
    0.67
     today
    0.67
    ;
    0.66
    Act Density 0.186%

    No Known Activations