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

    Neuronpedia

    INDEX
    Explanations

    references to specific physical elements or structures

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    farin
    -0.52
    swick
    -0.50
    Билгалдахарш
    -0.50
     affiliate
    -0.50
     Réponses
    -0.49
     обстоя
    -0.49
    
    -0.49
     referido
    -0.47
     frequenza
    -0.46
    ürd
    -0.46
    POSITIVE LOGITS
     zitten
    0.73
     enthalten
    0.60
    τώ
    0.57
     Contains
    0.56
     contains
    0.55
     contain
    0.54
     iprot
    0.53
    اوية
    0.53
    Portály
    0.52
     Référence
    0.51
    Act Density 0.153%

    No Known Activations