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

    Neuronpedia

    INDEX
    Explanations

    dates and specific terms related to laws or policies

    oai_token-act-pair · gpt-3.5-turbo

    key themes related to education, policy, and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.58
    atile
    -0.51
    bidden
    -0.49
    ospital
    -0.47
    rouse
    -0.47
    essage
    -0.45
    quartered
    -0.45
     Ezek
    -0.45
     recalled
    -0.45
    itored
    -0.44
    POSITIVE LOGITS
     ðŁĻĤ
    0.71
     :)
    0.66
     ;)
    0.66
     ðŁĺ
    0.64
    !!!
    0.61
     tho
    0.61
     folks
    0.60
     :-)
    0.59
     stupidity
    0.58
    !)
    0.58
    Act Density 1.316%

    No Known Activations