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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts associated with architectural structures in neural networks

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.77
    __':
    -0.67
    Personensuche
    -0.64
    IsContent
    -0.60
     Normdatei
    -0.52
     protoimpl
    -0.52
     Pristupljeno
    -0.52
    :✨
    -0.52
    aarrggbb
    -0.51
     altrett
    -0.51
    POSITIVE LOGITS
    GenerationType
    0.62
     Shah
    0.52
    posedge
    0.51
    ASHI
    0.50
     individually
    0.50
    Herzlich
    0.49
    oforte
    0.48
    esthetic
    0.47
     accurately
    0.47
     Properly
    0.47
    Act Density 0.368%

    No Known Activations