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

    Neuronpedia

    INDEX
    Explanations

    references to figures or tables in academic or technical documents

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Geplaatst
    -0.58
     ritorno
    -0.56
     يتيمه
    -0.56
    וויק
    -0.54
     noqa
    -0.52
     utafitiHapana
    -0.51
     contoh
    -0.50
    ēj
    -0.50
     pertes
    -0.49
     pprint
    -0.49
    POSITIVE LOGITS
     contextLoads
    0.77
    WindowConstants
    0.71
    RuleContext
    0.66
    ']>;
    0.65
    theless
    0.63
     Hout
    0.60
     obstante
    0.59
     Yol
    0.58
    FilterChain
    0.57
    );
    0.56
    Act Density 0.002%

    No Known Activations