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

    Neuronpedia

    INDEX
    Explanations

    different forms of the word "para" related to chemical structures

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    anía
    -0.79
    edip
    -0.74
    DUC
    -0.74
     Orrell
    -0.70
     secco
    -0.69
    rajz
    -0.69
     Ortiz
    -0.68
    manship
    -0.67
    cplusplus
    -0.67
     Ruskin
    -0.67
    POSITIVE LOGITS
    para
    1.61
    Para
    1.55
     Para
    1.52
     para
    1.43
     PARA
    1.38
    PARA
    1.38
     paradigms
    1.05
     PARAD
    0.99
     Paradigm
    0.98
     parag
    0.96
    Act Density 0.017%

    No Known Activations