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

    Neuronpedia

    INDEX
    Explanations

    dates in text

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical values and certain dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TERN
    -0.65
    Reloaded
    -0.62
    ãĤ£
    -0.61
    irlf
    -0.61
     moth
    -0.61
     decaying
    -0.59
     phosphorus
    -0.59
    ander
    -0.59
    phia
    -0.58
    aminer
    -0.58
    POSITIVE LOGITS
    iste
    0.65
    ixt
    0.63
    aroo
    0.63
    arter
    0.63
    liga
    0.61
    govtrack
    0.59
    ente
    0.59
    alias
    0.58
    ESE
    0.57
    ãĤ¤ãĥĪ
    0.57
    Act Density 0.455%

    No Known Activations