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

    Neuronpedia

    INDEX
    Explanations

    versions or iterations of things

    oai_token-act-pair · gpt-3.5-turbo

    references to different versions of something, particularly applications or media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Scotland
    -0.80
    atoon
    -0.69
    among
    -0.66
    ample
    -0.65
    adish
    -0.64
    puff
    -0.63
    chester
    -0.62
     alone
    -0.62
    ogh
    -0.62
     tears
    -0.62
    POSITIVE LOGITS
     same
    0.90
     latter
    0.87
     infamous
    0.80
    ORY
    0.80
     aforementioned
    0.80
     entire
    0.79
     Infinite
    0.79
     contents
    0.77
     proverbial
    0.73
     dreaded
    0.72
    Act Density 0.331%

    No Known Activations