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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the timing of future events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to future events or expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sacrific
    -0.66
     Rings
    -0.62
     Rack
    -0.61
     dare
    -0.61
     constantly
    -0.59
     continually
    -0.58
    pired
    -0.58
     filib
    -0.57
     hemor
    -0.57
     simulated
    -0.56
    POSITIVE LOGITS
     enough
    0.90
     ðŁĻĤ
    0.89
     ;)
    0.88
     :)
    0.86
    2019
    0.85
    EDIT
    0.84
    !
    0.83
     :-)
    0.81
    est
    0.78
    .
    0.77
    Act Density 0.072%

    No Known Activations