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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of "som" or specific references like "Somerville" and "Somme"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Som" or "somatic" concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UID
    -0.71
     Lovecraft
    -0.66
    holder
    -0.65
     negligence
    -0.65
     Thumbnails
    -0.61
    BOOK
    -0.60
     secrecy
    -0.60
     misleading
    -0.58
     gallery
    -0.57
     decaying
    -0.56
    POSITIVE LOGITS
    ority
    1.17
    essage
    1.14
    asaki
    1.09
    eday
    1.09
    oda
    1.08
    atos
    1.04
    ilitary
    1.04
    ber
    1.04
    oleon
    1.02
    ming
    1.02
    Act Density 0.021%

    No Known Activations