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

    Neuronpedia

    INDEX
    Explanations

    references to organizational support or collaboration in projects

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     wikipagina
    -0.81
    expandindo
    -0.81
     Majefty
    -0.75
    клопе
    -0.73
     ſtate
    -0.70
     beginnetje
    -0.69
     تانيه
    -0.69
    ​—
    -0.69
     themſelves
    -0.68
     auffi
    -0.67
    POSITIVE LOGITS
     sentimos
    0.50
     and
    0.50
    iedz
    0.48
     felt
    0.47
     dynamic
    0.47
     re
    0.47
     so
    0.46
    yid
    0.46
     &
    0.45
     due
    0.45
    Act Density 0.202%

    No Known Activations