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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases or instances

    oai_token-act-pair · gpt-3.5-turbo

    references to specific points in time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cav
    -0.70
     è£ıç
    -0.69
    oppable
    -0.68
    rone
    -0.66
    tur
    -0.63
     reside
    -0.61
    ibaba
    -0.60
    itives
    -0.60
    uras
    -0.58
    xual
    -0.58
    POSITIVE LOGITS
    OOD
    0.64
    YN
    0.63
    wise
    0.62
     Means
    0.62
    committee
    0.61
    LEY
    0.60
     Exposure
    0.60
     Logged
    0.60
    VERTISEMENT
    0.60
    chn
    0.59
    Act Density 0.055%

    No Known Activations