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

    Neuronpedia

    INDEX
    Explanations

    the word "from"

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "from."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rongh
    -0.67
    ratulations
    -0.64
    escription
    -0.57
    idate
    -0.57
    leneck
    -0.57
    faced
    -0.57
    inen
    -0.57
    isphere
    -0.56
    opoly
    -0.56
    emetery
    -0.56
    POSITIVE LOGITS
     afar
    1.04
     whence
    0.92
     thence
    0.82
     abroad
    0.67
     inside
    0.64
     scratch
    0.64
     within
    0.60
     atop
    0.59
     elsewhere
    0.57
     anywhere
    0.55
    Act Density 0.134%

    No Known Activations