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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating a positive or negative outlook or prediction regarding future events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating prognosis or predictions about outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ventus
    -0.82
    ELF
    -0.76
    isons
    -0.74
    ãĤ´
    -0.74
    ategory
    -0.73
    velength
    -0.73
    ĸļ
    -0.73
    Reviewer
    -0.70
    igent
    -0.70
    aditional
    -0.70
    POSITIVE LOGITS
     future
    0.96
     doom
    0.90
     sunset
    0.81
     rebound
    0.80
     2020
    0.78
     prospects
    0.77
     2019
    0.77
     Future
    0.77
     fortun
    0.76
     tomorrow
    0.74
    Act Density 0.519%

    No Known Activations