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

    Neuronpedia

    INDEX
    Explanations

    words related to future predictions

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the concept of "one day."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    listed
    -0.71
    agara
    -0.67
    rador
    -0.66
    arial
    -0.66
    iste
    -0.64
    reb
    -0.64
    erville
    -0.60
    er
    -0.59
    ega
    -0.58
    ania
    -0.57
    POSITIVE LOGITS
     day
    1.07
     DAY
    0.85
    day
    0.84
     millisec
    0.79
     moment
    0.75
     Day
    0.75
    Day
    0.74
     heartbeat
    0.74
    ·
    0.74
     )))
    0.69
    Act Density 0.319%

    No Known Activations