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

    Neuronpedia

    INDEX
    Explanations

    dates and events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    obal
    -0.73
    xual
    -0.71
     bribe
    -0.67
    afety
    -0.63
    ãĥ³ãĤ¸
    -0.62
    pecially
    -0.62
     Cosponsors
    -0.61
     reproduced
    -0.60
    cham
    -0.60
     reprodu
    -0.59
    POSITIVE LOGITS
    iatus
    0.93
     underway
    0.91
     waning
    0.89
     looming
    0.85
     imminent
    0.84
     anniversary
    0.83
     TBD
    0.81
     adjourn
    0.78
     countdown
    0.77
    oldown
    0.77
    Act Density 0.224%

    No Known Activations