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

    Neuronpedia

    INDEX
    Explanations

    personal experiences or events described in a narrative format

    oai_token-act-pair · gpt-3.5-turbo

    subjective experiences or emotional states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     favoured
    -0.50
     QC
    -0.49
     rumours
    -0.49
     apologise
    -0.46
     Australians
    -0.46
     organisers
    -0.46
     travellers
    -0.45
    iverpool
    -0.45
     apologised
    -0.44
     flavours
    -0.43
    POSITIVE LOGITS
    icidal
    0.47
     srfAttach
    0.46
    bors
    0.46
    isite
    0.45
    weak
    0.45
    doctoral
    0.43
    idated
    0.43
    visors
    0.43
    Notice
    0.42
    gency
    0.42
    Act Density 1.362%

    No Known Activations