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

    Neuronpedia

    INDEX
    Explanations

    keywords related to specific geographical locations and entities

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    mau
    -0.54
     Mohd
    -0.54
     Parrish
    -0.54
     McInt
    -0.50
    ייט
    -0.50
     comptes
    -0.49
     toxic
    -0.49
     Siegfried
    -0.49
    perms
    -0.49
    ferrer
    -0.49
    POSITIVE LOGITS
     Ethiopia
    1.49
     Ethiopian
    1.34
    Ethiopia
    1.33
     Ethio
    1.20
    Ethio
    1.18
     Addis
    1.07
     Ababa
    0.98
     Desta
    0.77
     ddelweddau
    0.74
    ibouti
    0.73
    Act Density 0.022%

    No Known Activations