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

    Neuronpedia

    INDEX
    Explanations

    references to physical characteristics and body movements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.65
     hand
    -0.55
     handed
    -0.55
     hands
    -0.54
    istoitu
    -0.54
    Przypisy
    -0.53
     tangga
    -0.53
    Dab
    -0.53
    amot
    -0.53
    ForValue
    -0.52
    POSITIVE LOGITS
    Autoritní
    0.68
     Paglinawan
    0.53
     Beller
    0.50
    enchymal
    0.49
     adresa
    0.48
     energética
    0.47
     collapses
    0.47
     escolar
    0.47
    setlength
    0.46
    swagger
    0.46
    Act Density 0.012%

    No Known Activations