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

    Neuronpedia

    INDEX
    Explanations

    years or dates

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years or time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     snipp
    -0.62
     Wem
    -0.56
    imore
    -0.54
     Pru
    -0.53
    Jackson
    -0.52
    Pack
    -0.52
     dy
    -0.51
    umbn
    -0.51
    ashtra
    -0.51
     Dil
    -0.50
    POSITIVE LOGITS
     onwards
    1.00
     onward
    0.89
    âĢ²
    0.79
     inception
    0.73
    when
    0.71
    -'
    0.67
    iatus
    0.64
    quist
    0.62
    staking
    0.60
    .
    0.60
    Act Density 0.095%

    No Known Activations