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

    Neuronpedia

    INDEX
    Explanations

    references to geographical or location-based terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     StringTokenizer
    -0.46
    Rüyada
    -0.41
     Minaj
    -0.40
    boutin
    -0.38
    veston
    -0.37
     pubblicazione
    -0.37
    Dallas
    -0.37
    bergement
    -0.36
    Numerade
    -0.36
    ceğine
    -0.36
    POSITIVE LOGITS
     Himalayan
    0.67
     Himalayas
    0.65
     disambiguazione
    0.63
     Uttarakhand
    0.63
    Himal
    0.63
     Himalaya
    0.58
     Corbett
    0.56
     Himachal
    0.56
     Kuma
    0.56
    Източници
    0.55
    Act Density 0.161%

    No Known Activations