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

    Neuronpedia

    INDEX
    Explanations

    mention of specific time periods or dates

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating approximate future timeframes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ettel
    -0.84
    iv
    -0.83
    esc
    -0.82
    andi
    -0.81
    edes
    -0.81
    iants
    -0.80
    raid
    -0.80
    abal
    -0.79
    racted
    -0.78
    ortium
    -0.77
    POSITIVE LOGITS
     ago
    0.78
    theless
    0.77
     periods
    0.75
     mornings
    0.73
     else
    0.72
     unspecified
    0.72
     hereafter
    0.72
     Ago
    0.71
     sometime
    0.69
     later
    0.68
    Act Density 0.017%

    No Known Activations