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

    Neuronpedia

    INDEX
    Explanations

    phrases related to different variations of the word "life"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to life experiences or narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Quantity
    -0.74
    anton
    -0.73
    antics
    -0.73
    oppable
    -0.72
    amination
    -0.72
    ovan
    -0.70
    omatic
    -0.68
    ador
    -0.68
     Machines
    -0.67
    leaders
    -0.66
    POSITIVE LOGITS
    llor
    0.82
    zie
    0.72
    lessly
    0.72
    mite
    0.70
    yer
    0.69
    ly
    0.69
    tta
    0.68
    nsics
    0.67
    nsic
    0.67
    hei
    0.65
    Act Density 0.045%

    No Known Activations