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

    Neuronpedia

    INDEX
    Explanations

    words related to derivation or origin

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "from" indicating the origin or source of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leneck
    -1.04
    mouth
    -0.99
    facing
    -0.82
    faced
    -0.81
    seek
    -0.78
    priority
    -0.77
    olson
    -0.76
    queue
    -0.75
    airs
    -0.73
    isphere
    -0.73
    POSITIVE LOGITS
     scratch
    1.09
     afar
    0.97
     thence
    0.92
     whence
    0.83
     atop
    0.75
     conception
    0.72
     elsewhere
    0.71
     abroad
    0.70
     Shutterstock
    0.69
     within
    0.68
    Act Density 0.132%

    No Known Activations