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

    instances of the word "from" indicating source or origin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disson
    -0.69
    tions
    -0.67
    rises
    -0.66
     VIDEOS
    -0.66
    ãĤ´ãĥ³
    -0.64
    terness
    -0.62
     assumes
    -0.62
     accompanies
    -0.61
    nir
    -0.60
     reacts
    -0.60
    POSITIVE LOGITS
    liest
    0.91
    ensual
    0.79
    ivated
    0.71
    avering
    0.70
    ivable
    0.69
    erest
    0.68
    lain
    0.67
    ivating
    0.66
    oult
    0.64
    inently
    0.63
    Act Density 0.119%

    No Known Activations