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

    Neuronpedia

    INDEX
    Explanations

    references to academic journals

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     végétale
    -0.68
     referenties
    -0.59
     spéciale
    -0.58
     doccia
    -0.57
     tecnici
    -0.57
     avoient
    -0.54
     aveug
    -0.53
     légale
    -0.52
     defaultstate
    -0.51
     sexuelle
    -0.51
    POSITIVE LOGITS
    journal
    1.09
     Journal
    0.86
    Journal
    0.83
     journal
    0.75
     propOrder
    0.75
     JOURNAL
    0.72
    /*
    0.68
    JOURNAL
    0.66
    vement
    0.65
     Jornal
    0.64
    Act Density 0.001%

    No Known Activations